Peer Revenue Impact factor: volatile

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Information Retrieval

cs.IR Watch Information Retrieval

Saturday 8 August

Information Retrieval

Search over the Visual World: Persistent Visual Memory, Layered Indexes, and Source-Grounded Evidence

Sankalp Nagaonkar, Rohit Garg, Ankit Raj et al. (+2 more)

Most video-retrieval systems assume a bounded corpus and return ranked files or timestamps. Agents operating over cameras, screens, streams, and archives face a different systems problem: observations arrive continuously; models interpret them at different temporal granularities; context must be selected without replaying the complete visual record; and results must stay connected to inspectable source evidence. We argue that search over such a corpus is an infrastructure problem that cannot be reduced to ranking video files. We develop a conceptual and formal model of search over the visual world built on analyzer-defined scenes, persistent understanding artifacts, visual memory as coexisting scene spaces over shared source time, and capability-declared indexes, distinguishing memory (everything retained), context (what is selected for a task), and evidence (the source intervals that ground it). The VideoDB data format (VDB) realizes this model in production, exposed through a typed search surface spanning planned retrieval, stateful investigation, direct access, and grounded synthesis. We contrast this model-agnostic infrastructure, where segmentation, sampling, model choice, embeddings, and ranking are system decisions and live streams are first-class sources, with video-native foundation models offered as fixed APIs. In a semantic-retrieval comparison against a commercial video-native engine spanning 9,800+ queries over four public datasets, a pipeline of general-purpose components achieves higher macro-averaged Recall@1/@3/@10 (73.09/83.39/91.20 versus 65.75/77.13/89.10), while the baseline is higher at Recall@50 (96.42 versus 96.07). Retrieval quality over the visual world is today governed more by system design than by video-specific pretraining, and visual-memory infrastructure can deliver it while keeping playable, source-grounded evidence first-class.
Read the full abstract

All authors Sankalp Nagaonkar, Rohit Garg, Ankit Raj, Ashish Choithani, Ashutosh Trivedi

Information Retrieval

Give the Long-tail More SPACE: Promoting Provider Fairness in Next POI Recommendation

Anran Zhang, Jiaqi Jiang, jiahui Jin et al. (+1 more)

Next point-of-interest (POI) recommendation predicts users' future destinations from historical mobility sequences and has become a key component of location-based services. However, mainstream models often concentrate exposure on a small set of popular POIs, leaving long-tail merchants systematically under-exposed. While provider fairness has recently attracted increasing attention, directly applying existing provider-fairness techniques to POI recommendation is problematic: (i) users face execution constraints; and (ii) POIs face resource supply constraints. To address this, we propose SPACE (Supply- and Physics-Aware Conditional Embedding generation), a model-agnostic framework that improves long-tail POI exposure via virtual user generation under explicit feasibility and supply control. SPACE consists of three stages: (1) community inference to capture heterogeneous user execution constraints; (2) unbalanced optimal-transport allocation to decide how many virtual users each tail POI should receive from which communities under POI-specific supply budgets; and (3) constraint-guided latent diffusion to generate POI-conditional, community-consistent virtual user embeddings. The generated user-POI pairs can be seamlessly used to train existing recommenders without modifying their architectures. Extensive experiments on three real-world datasets demonstrate that SPACE substantially improves provider fairness while maintaining and often improving recommendation accuracy across multiple backbone models. Our code is publicly available at https://github.com/Anniran1/SPACE-main.
Read the full abstract

All authors Anran Zhang, Jiaqi Jiang, jiahui Jin, Yuhan Zhao

Information Retrieval · Cross-listed from cs.AI

VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge

Wenqi Chen, Haofei Yang, Rui Yang et al. (+1 more)

Retrieval-Augmented Generation (RAG) is essential for enterprise knowledge question answering (QA), particularly in domains with complex product documentation like telecommunications. However, existing RAG approaches largely overlook the holistic integration of diverse retrieval strengths, leading to inaccurate domain routing, poor utilization of hierarchical document structures, and consequently limited reasoning capabilities over enterprise knowledge. To address these limitations, we present VDGR-RAG, which integrates vector retrieval, directory-driven reasoning, graph traversal, and iterative reflection in a unified framework for accurate enterprise knowledge QA. Specifically, VDGR-RAG is an agentic GraphRAG system that first constructs a Hierarchical Heterogeneous Knowledge Graph ($\text{H}^2$KG) from document chunks to preserve both hierarchical directory structures and semantic relationships, and then employs a set of atomic tools for knowledge retrieval that can be freely composed to navigate the $\text{H}^2$KG: (1) a directory-enhanced routing tool that uses table-of-contents (TOC) structures to route user queries to appropriate domain-specific $\text{H}^2$KGs; (2) a multi-route retrieval tool that combines vector search, TOC-based agentic search, and graph search for comprehensive knowledge retrieval; (3) a directory backtracking tool that corrects knowledge localization biases; and (4) a dynamic reflection tool that iteratively plans the next retrieval phase. We conduct extensive experiments on our enterprise product documents across four wireless domains (e.g., energy saving and fault management). Experimental results demonstrate that our method significantly outperforms a variety of RAG baselines in terms of both knowledge retrieval recall and QA accuracy.
Read the full abstract

All authors Wenqi Chen, Haofei Yang, Rui Yang, Fangming Li

Information Retrieval

PushDualGen: Enabling LLMs to Generate Semantic IDs with Interpretable Copy for Industrial Push Recommendation

Manjia Lin, Da Li, Yan Wang et al. (+9 more)

Push recommendation in KuaiShou proactively delivers personalized content to nearly one billion users to facilitate their engagement. Recently, generative recommendation has achieved end-to-end user personalization through semantic ID. However, their black- box characteristics make recommendation logics difficult to trace, hindering their deployment. OneRec-Thinking addresses this by incorporating CoT before generating SIDs, but this significantly increases inference cost. To support large-scale industrial applications, we propose PushDualGen, a lightweight generator, which first generates the SID and then produces a copy as a skippable explanation. PushDualGen has been deployed in Kuaishou's push recommendation system. Online A/B tests demonstrate the effectiveness of PushDualGen, delivering significant improvements in both user attraction and satisfaction. The effective play rate for videos recommended to users has relatively increased by 8.50%, while the dissatisfaction rate has relatively fallen by 37.70%. In the long term, PushDualGen optimises the content ecosystem, providing more exposure for long-tail videos.
Read the full abstract

All authors Manjia Lin, Da Li, Yan Wang, Yong Jin, Zheming Ding, Wei Yuan, Lei Yan, Yanan Xia, Lu Zhang, Fan Yang, Xuanping Li, Yanan Niu

Information Retrieval · Cross-listed from cs.AI

Guixu: Valuation-Driven Data Discovery for Autonomous AI Agents with On-Chain Attestation

Yifan Wu, Yuchen Peng, Jiaqi Chai et al. (+4 more)

Autonomous agents increasingly rely on external data to complete downstream tasks such as model training and decision support. However, existing data discovery systems remain largely retrieval-oriented: they surface candidate datasets from heterogeneous sources, but provide limited support for estimating task-specific utility, selecting cost-effective datasets under budget constraints, or incorporating trustworthy feedback from prior usage. This paper presents Guixu, a valuation-driven data discovery system for autonomous agents. Guixu employs a three-phase valuation pipeline with proxy-label propagation and multi-round knapsack optimization for task-aware data valuation. Guixu integrates agentic payment protocol to enable budget-constrained data procurement workflows. Guixu leverages on-chain data market and attestation signals for verifiable data discovery. Our demonstration highlights how Guixu enables an agent to move beyond keyword-based dataset retrieval toward task- and budget-aware, trustworthy data discovery and procurement. Attendees can interactively explore the full workflow, from NL task specification and multi-source search to data valuation and verifiable transaction feedback.
Read the full abstract

All authors Yifan Wu, Yuchen Peng, Jiaqi Chai, Yufei Qian, Xilin Li, Ke Chen, Lidan Shou

Information Retrieval · Cross-listed from cs.CV

How Much Does It Cost to Answer My Question? Benchmarking Cloud VLM-based VQA Systems

Henri Vanhuynegem, Weitao Xu, Yiran Shen et al. (+1 more)

Vision-language models (VLMs) are becoming a practical backend for mobile visual question answering (VQA) systems, enabling smartphones and smart glasses to answer users' questions about the physical world. Since modern VLMs remain difficult to run on mobile and edge devices, VQA systems increasingly offload inference to cloud-based VLMs. This gives mobile devices access to stronger computation, but it also makes visual input preparation a key system variable: how the image is prepared before offloading affects not only answer quality but also payload size, token cost, and system latency. Proprietary APIs expose little control over model internals or serving behavior, leaving client-side preprocessing as the main practical optimization space for downstream developers. Many such techniques have been proposed for visual offloading, yet their cost-quality impact on commercial cloud VLMs has never been studied. To fill this gap, we present VQABench, the first systematic benchmark that treats client-side input preprocessing as a controlled variable for cloud-VLM-based VQA. We evaluate 12 preprocessing techniques across three VQA datasets and four commercial VLMs from three providers, totaling 95,168 API calls. Our results show that preprocessing is not universally beneficial: its effectiveness depends on the target model, API paradigm, provider token-accounting rule, and task formulation. A poorly selected preprocessing strategy can increase deployment cost or latency while degrading answer accuracy. Overall, our benchmark clarifies when preprocessing helps, when it fails, and why, providing insights to guide future research and real-world deployment of VQA systems.
Read the full abstract

All authors Henri Vanhuynegem, Weitao Xu, Yiran Shen, Guohao Lan

Friday 7 August

Information Retrieval

The Utility of LLMs in Recommender Systems Explanation Evaluation

Kathrin Wardatzky, Oana Inel, Luca Rossetto et al. (+1 more)

Explanations play a crucial role in creating trustworthy recommender systems (RS), yet choosing a good explanation method presents challenges. Many explanation methods exist, but little guidance exists on which is best for which setting. Existing explanation generation methods often produce abstract outputs that require further formatting to become user-friendly, with a seemingly endless pool of options. Running user-based evaluations of all possible options is usually unfeasible, while automated evaluation metrics often either assess only the explainer's abstract output or require comparison with a ground truth, which is generally unavailable. Recent studies have shown that large language models (LLMs) can serve as “judges” for explanation evaluation, but their reliability has not yet been thoroughly explored. This paper studies the utility of LLMs in selecting an effective explanation method for a given application. We first explore their ability to generate explanation prototypes given varying information about the RS and the user. Specifically, we generate 18 distinct explanation prototypes, which are subsequently evaluated by 14 LLMs of varying sizes across two temperature settings. We compare these against human ratings derived from a user study. Our results show that while LLMs exhibit human-like rating patterns and achieve moderate rank correlation with human raters, their absolute rating agreement is low and varies substantially by model size and evaluation construct. We derive four practical recommendations: keep explanation-generation prompts concise, prefer larger models for evaluation, pre-test evaluation constructs, and audit explanations for factual accuracy, as neither humans nor LLMs reliably detect non-factual content.
Read the full abstract

All authors Kathrin Wardatzky, Oana Inel, Luca Rossetto, Abraham Bernstein

Information Retrieval

Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness

Srijith Ravikumar

LLM recommenders for top-K item suggestion regularly emit titles outside the target catalog. Prior audits report a binary out-of-domain rate; none ask whether the model knew. We jointly audit hallucination rate (OOD@10) and verbalized-confidence calibration (ECE, Brier, reliability) for four zero-shot LLM recommenders from four independent vendors (Mistral Large, Llama-3.3-70B, GPT-OSS-120B, Claude Sonnet 4.6), not grounded or fine-tuned systems, across three catalogs (MovieLens-25M, Amazon Reviews 2023 Toys, Yelp Open Dataset), stratified by item popularity. Measuring catalog membership is itself the hard part: on identical outputs the reported rate moves by an order of magnitude with the string matcher used, and F1 cannot separate the candidates. We validate the instrument against 201 human judgments and select on net bias, where the adopted one is off by -0.040 against +0.144 for the common fuzzy rule. Hallucination is then strongly catalog-dependent (0.6-2.7% on MovieLens, 11.6-38.7% on Yelp, 49.3-61.0% on Amazon Toys). Each model holds a near-constant confidence level barely responsive to the catalog, while the catalog-hit rate swings 60 points, so the sign of the error is set by where a model's constant lands against a catalog's accuracy: 7 of the twelve cells are under-confident and 5 over-confident, all four under-confident on MovieLens, all four over-confident on Amazon Toys. We read this as an elicitation mismatch: "Just Ask" elicits a generic quality rating, not a catalog-membership probability. A conformal abstention threshold over verbalized confidence changes hallucination by at most 1.65 pp across four alpha levels, because the channel cannot separate correct items from hallucinations. We recommend that audits report calibration alongside OOD, validate the matcher producing the OOD number, and use catalog-anchored elicitation.
Read the full abstract

2608.10008 · 7 Aug · Accepted at CIKM 2026 (short paper). v2 corrects the catalog-membership matcher, which scored truncated catalog entries as perfect matches to longer hallucinated titles. One finding reverses: v1 reported all four models under-confident in all twelve cells; v2 finds the catalog sets the direction. Amazon Toys hallucination moves from 4.5-8.3% to 49.3-61.0%. Cite v2 or later; v1 is superseded

Abstract PDF $HALU ×4$CELL ×1$DATA ×1

Information Retrieval

Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation

Donald Loveland, Liam Collins, Bhuvesh Kumar et al. (+2 more)

Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories. In these systems, items are often represented through semantic IDs (SIDs) added to the LLM vocabulary as special tokens. Ideally, SIDs imbue item token representations with semantic priors, thereby improving model generalization. However, standard vocabulary expansion typically initializes these tokens as random Gaussian vectors, discarding the SIDs' underlying continuous geometry and forcing the LLM to relearn token relationships from interaction data. To demonstrate the consequences of this design, we first show that training from this initialization tends to organize SID embeddings around item popularity rather than semantics. We further show that, despite partially reducing the reliance on popularity and improving cold item performance, the computationally expensive process of continual pretraining (CPT) fails to reliably recover the original semantic geometry. To address these findings, we propose a simple, parameter-free intervention that initializes SID token embeddings directly from their corresponding centroids in the semantic embedding space. Requiring only a few lines of code and no additional training or inference overhead, this drop-in approach improves pure-SFT Recall@5 by up to 16%, reaches peak performance with up to 40% fewer SFT steps, and improves cold-item Recall@5 by up to 60%. Moreover, on datasets that benefit from additional CPT, centroid initialization reaches comparable performance while requiring half as many CPT epochs. Together, our findings show that preserving SID geometry, beyond shared-prefix structure, provides a simple and effective semantic prior for LLM-based GR.
Read the full abstract

All authors Donald Loveland, Liam Collins, Bhuvesh Kumar, Danai Koutra, Neil Shah

Information Retrieval · Cross-listed from cs.AI

Controlled Memory Interference in Continual LLM Agents

Ao Ding, Hongzong LI, Shiqin Tang et al. (+4 more)

Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience. Yet memory evolution is not simply a process of storing more information: new experiences may reinforce, revise, or interfere with existing memory states. Existing systems mainly emphasize memory construction and relevance-based retrieval, but several memories may remain simultaneously relevant while differing in state, temporal validity, or authority. We introduce Controlled Memory Interference (CMI), a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships. Across controlled memory evolution, benign accumulation has limited effects, whereas relationship-specific interference sharply suppresses update plasticity with little stability gain, either by blocking target-memory exposure or by disrupting its downstream use. Lexical and Dense retrieval exhibit distinct interference pathways, while poisoning is more sensitive to update-authority cues than to recency alone. Beyond diagnosis, CMI provides targeted examples for interference-aware memory learning, improving the distinction between valid updates and interference-inducing memories while preserving performance on original memory tasks. These findings show that memory evolution is shaped not only by memory scale, but also by interactions among accumulated experiences. More broadly, memory interference emerges as an important factor for reliable continual agent memory systems.
Read the full abstract

All authors Ao Ding, Hongzong LI, Shiqin Tang, Li Zhang, Liang Chen, Xuyang Chen, Zi Liang

Information Retrieval · Cross-listed from cs.CL

CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG

Gyuwan Kim, Cheoneum Park and Tao Yang

Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant information redundancy and noise still remain in the coarse-grained chunks. This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG (Contextualized Information Nugget KV Cache Reuse for Long-Context RAG). The name metaphorically reflects our core mechanism: much like assembling small tokens (or "coins") to accumulate a larger value, CoinRAG compositionally reuses offline-computed, fine-grained nugget caches to form a learned contextual representation efficiently in a more semantically relevant but compact manner. Specifically, instead of full-chunk encoding, CoinRAG identifies query-relevant semantic units within retrieved chunks through two-stage retrieval and seamlessly assembles their sliced KV representations with a chunk-level context. Extensive evaluations on LongBench multi-hop question answering tasks demonstrate that CoinRAG significantly reduces operational costs and outperforms the other baselines with a new Pareto frontier and an average 5.3% relative improvement in answer quality (F1) under a standard fast prefill latency budget.
Read the full abstract

Information Retrieval · Cross-listed from cs.CV

Conformal Coverage Guarantees for Any Video Temporal Grounder

Aseel Mohamed, Rasul Khanbayov, Erchin Serpedin et al. (+1 more)

Event boundaries in continuous video are ambiguous: re-annotate the same query-video pair and independent annotators mark moments that overlap by less than half on a large fraction of samples. The ground truth for video temporal grounding is therefore a distribution over intervals, yet every grounder returns a single interval with no statement of reliability, so at deployment a wrong interval is indistinguishable from a right one. COVER changes the output object: a post-hoc, model-agnostic wrapper that turns any grounder, a trained localizer or a black-box video–language model, into one that emits a temporal region containing the true moment with probability at least $1-\alpha$, by calibrating the quantile of a temporal nonconformity score on held-out labels and widening the base prediction by that amount. The guarantee is finite-sample and distribution-free under exchangeability, and requires neither retraining nor white-box access. We give two score families, a two-sided boundary-widening score for grounders that emit an interval and a super-level-set score for grounders that emit a relevance signal, and develop theory specific to grounding that bounds how large the certified region becomes, when coverage survives conditioning on event length, and how it degrades when moments from one video break exchangeability. Across three benchmarks and five grounders, realized coverage tracks the target, and calibration exposes what point metrics hide.
Read the full abstract

All authors Aseel Mohamed, Rasul Khanbayov, Erchin Serpedin, Hasan Kurban

Information Retrieval · Cross-listed from cs.AI

GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks

Rodrigo Ferreira Rodrigues, Karim Radouane, Jose G Moreno et al. (+1 more)

In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited insights into their generalization capabilities. In this paper, we present \benchName, a comprehensive benchmark for probing LLMs on geo-related tasks. We leverage a careful selection of twelve publicly available datasets from diverse geo-related tasks and domains, and evaluate a set of LLMs on geo-spatial and temporal understanding using our benchmark. Our results show that reasoning and size have a strong impact on overall performance. GeoBenchLLM is publicly available at https://github.com/Rfr2003/GeoBenchLLM.
Read the full abstract

All authors Rodrigo Ferreira Rodrigues, Karim Radouane, Jose G Moreno, Lynda Tamine

Information Retrieval · Cross-listed from cs.CL

Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding

Karim Radouane, Jose G Moreno and Lynda Tamine

Understanding concepts is fundamental to generalization. Despite their impressive performance on a wide range of tasks, Large Language Models (LLMs) still struggle with genuine concept understanding. Prior work has evaluated conceptual understanding in LLMs using natural-language benchmarks or narrowly scoped synthetic tasks, but these settings often conflate multiple skills or lack precise control over the underlying concepts and their properties. To support controlled probing of concepts in LLMs, we design tests on their core properties: abstraction, compositionality, and groundness. We set up a concept-centric benchmark, targeting spatial concepts such as direction, distance, topology, and their compositions, and use question answering tasks serving as a proxy. We conduct extensive experiments across multiple LLM architectures and training regimes to analyze how model scale and design impact conceptual understanding. The results reveal clear limitations in current LLMs and provide insights into the factors shaping their ability to acquire and compose structured concepts. Our findings shed light on how concept-based LLMs can be redesigned for improved information access and knowledge management. The code will be available at https://github.com/rd20karim/concept-probing.
Read the full abstract

Information Retrieval

Exact Adaptive Hybrid Retrieval Without Fixed Top-L Cutoffs

Chunran Zhang

Modern retrieval-augmented generation (RAG) systems often fuse fixed Top-$L$ results from dense and sparse retrievers, treating later contributions as zero. The cutoff therefore determines both the ranking and its execution cost. Yet truncated fusion is not generally equivalent to complete-list fusion: unread cross-list ranks can change Top-$K$ membership or order even when the observed candidates contain every item in the complete-list Top-$K$. Because channel rankings vary across queries and corpus updates, a depth selected from historical queries may not transfer reliably. We propose Exact Adaptive Hybrid Retrieval (EAHR), which fixes the ordered Top-$K$ defined by complete-list weighted RRF as the retrieval target and treats channel depth as request-specific execution state. Per-Vector Scalar Quantization (PVS) and Posting Block-Max (PBM) produce resumable exact dense and sparse rankings. Fusion bounds unread contributions and requests further ranks only while they can change the Top-$K$. Every successful request therefore matches complete-list fusion without a preset Top-$L$; otherwise, execution continues safely to list exhaustion. Across five test collections and five temporal corpus snapshots, complete-list weighted RRF remained competitive, whereas fixed depths selected from historical queries did not transfer reliably. EAHR reproduced the complete-list ordered Top-20 in all 150 query-snapshot combinations. Under a warm-cache, interleaved, order-balanced protocol, the paired geometric-mean latency ratios of exhaustive batch execution to EAHR were 23.35 on TREC-DL 2019 and 30.28 on TREC-DL 2020. Anti-correlated rankings exhausted both lists, and some difficult queries were slower with EAHR. EAHR does not guarantee a speedup for every request; it fixes the exact result while adapting execution depth to the current rankings.
Read the full abstract

Information Retrieval

Invisible to the Machine: Auditing AI Restaurant, Cafe, and Bar Recommendation Against a Complete Market Census

Vladimir Pitenin

AI assistants are becoming a primary interface for local discovery, yet almost nothing is known about which venues they surface – especially in food and drink, where recommendations carry direct revenue consequences. We present the first census-denominated audit of AI venue recommendation: a complete enumeration of 4,776 cafes, restaurants, and bars across two bounded markets (Canggu and Ubud, Bali), against which we evaluate 2,208 search-grounded responses from four production AI systems (ChatGPT, Claude, Gemini, Perplexity) to 96 persona-conditioned queries, collected over seven days under a pre-registered protocol. Because we observe the full market, we can measure what sampled audits cannot: 85.6% of venues were never recommended by any system – 72.6% even among established venues with fifty or more ratings. Visibility follows a two-margin structure. Entry into answers is associated with documentation: review volume (OR 1.64), an own website (OR 1.92), listed price information (OR 1.54), and third-party web mentions (OR 1.44) – while star rating is null at this margin (OR 0.89). Rank within answers reverses the pattern: among recommended venues, rating significantly predicts first position (OR 1.17). Presence in an open POI dataset (Foursquare), a folk-theorized visibility factor, shows no positive effect at either margin. Outright fabrication is rare (0.08% of mentions), but systems recommended permanently closed venues 93 times – staleness, not hallucination, is the practical failure mode. Cross-system agreement is low (top-20 Jaccard 0.33-0.54). A two-week test-retest shows cross-period answer similarity comparable to same-day rerun similarity: the churn is sampling stochasticity, not temporal drift. We release our protocol, registry construction method, and derived data.
Read the full abstract

Information Retrieval · Cross-listed from cs.AI

DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding

Hanshu Yao, Janfeng Zhong, Niu Lian et al. (+1 more)

Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static retrieval and fragile cross-round memory. Mainstream single-round methods commit to a fixed top-$k$ page set at the outset and struggle to recover from early retrieval errors; recent iterative approaches allow multi-round evidence acquisition, but they do not investigate the propagation mechanism of cross-round states, making it difficult to track the dynamic changes in page relevance. To address these limitations, we propose DocMemo, a memory-guided framework that formulates long-document reasoning as dynamic evidence exploration. DocMemo maintains a tri-level retrieval state consisting of Document Schema Memory, Page Belief Memory, and Question Episodic Memory, which respectively capture structural priors, dynamic relevance estimation, and query-specific reasoning trajectories. During reasoning, DocMemo continuously refines cross-round page selection through Bayesian page belief updating with Thompson sampling, spatial proximity propagation, and structure-aware adaptive-granularity evidence access, while supplementing page-level evidence with fine-grained visual regions. Experiments on 3 benchmarks show that DocMemo achieves state-of-the-art performance and validate the efficacy of structured memory and dynamic page belief updating. Code is available at https://github.com/Harrygof/DocMemo.
Read the full abstract

All authors Hanshu Yao, Janfeng Zhong, Niu Lian, Jinpeng Wang

Information Retrieval

Teacher Retains Full Tokens, Student Merges Efficiently: TM20K for E-Commerce Sequence Modeling in Ad Recommendation

Xinchun Li, Duoru Zheng, Wenlin Zhao et al. (+13 more)

Benefiting from ultra-long behavior sequence modeling, existing recommender systems bring users a better experience via simultaneously considering their long-term and short-term interests. Nevertheless, extended sequence lengths introduce substantial burdens on training efficiency and serving throughput. Prior approaches typically utilize search-based or cluster-based compression on ultra-long sequences at the cost of fine-grained information, or rely on various lightweight target attention structures incapable of sufficient sequential feature extraction. In this paper, we balance the effectiveness and efficiency for ultra-long sequence modeling via full transformer modeling accompanied with a two-stage knowledge distillation framework. First, both teacher and student models take the full attention mechanism rather than pure target-sequence attention for effective sequence scaling. For student models, we propose several simple yet well-motivated token merge approaches, significantly compressing the sequence length while maintaining an acceptable performance. Then, a one-time teacher is heavily trained with full sequence tokens, further boosting the performance of student models via knowledge distillation. The proposed paradigm named TM20K has been successfully deployed in ByteDance's e-commerce advertising recommender system that extends the e-commerce sequence length to 20K, delivering substantial improvements in key business metrics (e.g., ADSS +1.036%) while keeping the training and serving cost nearly the same as the online state-of-the-art model (e.g., serving latency only +5.6%).
Read the full abstract

All authors Xinchun Li, Duoru Zheng, Wenlin Zhao, Haoran Ding, Ziyi Zhou, Jingxuan Tan, Huizhi Yang, Yuchen Jiang, Zhe Chen, Yuchao Zheng, Linlan Chen, Dongjian Wang, Dongyue Wang, Xiaosong Li, Hongyue Mao, Yaocheng Tan

Information Retrieval

MISO: Model-Internal-State-Guided Optimization for Ranking Models

Yongzhe Zhang, Xiaoyu Deng, Yifan He et al. (+29 more)

Ranking models are repeatedly refined within established model families, yet the choice of which component to scale, replace, or retire is often guided by expensive trial-and-error. We present Model Internal State Optimization (MISO), a systems workflow that uses model internal states (MIS), including parameters, activations, gradients, and normalization statistics, to prioritize such local optimization decisions. MISO extracts MIS from a trained ranking model, aggregates them into ranking, alignment, and comparison signals, and converts those signals into a small set of interpretable candidate edits. Because MIS are re-extracted after each retraining cycle, MISO naturally supports an adaptive optimization workflow that tracks evolving model behavior as data distributions and system requirements shift over time. In an ads ranking case study, MISO improves normalized entropy while requiring substantially fewer validation runs than expert-driven and black-box scaling workflows, offering a practical middle ground between manual tuning and opaque automated search.
Read the full abstract

All authors Yongzhe Zhang, Xiaoyu Deng, Yifan He, Mengying Sun, Sheng Luo, Yijia Liu, Hao Yan, Zhuo Li, Huiping Yao, Swathi Hrishikesh, Jing Chen, Dennis Choi, Steven Liu, Zhiwen Chen, Yang Jin, Haoyu Zhou, Lexi Luo, Keyi Chen, Anish Khazane, Marcio Porto, Xiaoya Wang, Emmy Wang, Jiang Liu, Kangfu Zheng, Xingyuan Wang, Peggy Yao, Yi Meng, Bilal Fadlallah, Gursharan Singh, Prabhakar Goyal, Alireza Vahdatpour, Santanu Kolay

Information Retrieval

Hierarchical Quantization with Domain-Adaptive Sparse Routing for Generative Cross-Domain Recommendation

Haiying He, Xiaopeng Li, Yuchen Gu et al. (+9 more)

Generative Recommendation (GenRec) represents a promising paradigm that achieves remarkable empirical success by encoding items as compact Semantic IDs (SIDs) and modeling user behavior via next-token prediction across diverse recommendation scenarios. Extending this paradigm to cross-domain recommendation is challenging because a unified model must accommodate heterogeneous item semantics and behavioral patterns across domains. Existing methods commonly rely on globally shared representations or lightweight domain adaptation, which may provide insufficient capacity for modeling heterogeneous patterns at different semantic granularities. To address these challenges, we propose HD-Rec, a unified generative framework for cross-domain recommendation. HD-Rec employs a hierarchical domain-aware quantizer that constructs semantic identifiers using globally shared coarse-level codebooks and adaptively routed fine-level codebooks. It further introduces a domain-adaptive sparse mixture-of-experts module that combines a continuously activated shared expert with a dynamically selected specialized expert. To improve the coherence of multi-token item representations, we develop a cross-granularity routing consistency objective that regularizes token-level routing decisions toward their item-level consensus. Experiments on three public cross-domain recommendation benchmarks show that HD-Rec consistently improves over competitive sequential, generative, and cross-domain recommendation baselines.
Read the full abstract

All authors Haiying He, Xiaopeng Li, Yuchen Gu, Kuo Cai, Bo Chen, Jingtong Gao, Yejing Wang, Derong Xu, Ruiming Tang, Guorui Zhou, Han Li, Xiangyu Zhao

Information Retrieval

From Classification to Recommendation: Empirical Analysis of Audio Embedding Models Application for Content-Based Music Recommendation

Qingrui Li, Haowei Lou, Chengkai Huang et al. (+2 more)

Pretrained audio representation models learned from large-scale corpora have achieved strong performance in audio classification and understanding. However, most existing models are optimized for objectives such as masked prediction, contrastive learning, or audio-text alignment, which do not necessarily produce representation spaces well-suited to recommender systems. Unlike classification, music recommender systems must capture item relationships shaped by subjective and behavior-dependent listener preferences. Although pretrained audio embeddings have been explored in conventional recommender systems, their effectiveness in the rapidly emerging paradigm of generative recommender systems remains underexplored. To address this gap, we systematically evaluate six representative audio encoders across three types of music recommender systems: content-based, sequential, and Semantic-ID-based generative recommender systems. We further investigate how residual-quantization design, including codebook width, quantization depth, and retained Semantic-ID prefixes, affects the preservation of recommendation-relevant information. Experiments on two music recommendation datasets show that audio-text-aligned and music-domain representations are generally more effective when pretrained embedding geometry is used directly, whereas interaction-based sequential training substantially reduces performance differences among encoders. We also find that increasing Semantic-ID capacity does not consistently improve generative recommender systems and may introduce substantial instability. These findings provide practical guidance for selecting audio encoders and designing audio-derived Semantic IDs for modern music recommender systems.
Read the full abstract

All authors Qingrui Li, Haowei Lou, Chengkai Huang, Quan Z. Sheng, Lina Yao

Information Retrieval

BZKO: An Ontology for the Card Index of German Post-War Compensation Records

Dilek Yargan, Jörg Waitelonis, Mahsa Vafaie et al. (+1 more)

The Central Federal Card Index (Bundeszentralkartei) of Germany is a key archival resource documenting compensation claims submitted by victims of National Socialist persecution and their relatives, within the German Wiedergutmachung process. To enable semantically enriched representation, integration, and reuse of this historically significant collection, we present the BZK Ontology (BZKO). We propose a two-layer ontology for historical archival data that separates ontologically grounded domain semantics from interoperability-oriented extension constructs. The approach combines BFO-based realism with archival standards (RiC-O, PROV-O, PiCo), enabling provenance-preserving semantic integration, while maintaining logical rigor, modularity, and reuse across digital humanities infrastructures. The proposed approach establishes a reusable semantic foundation for the integration of Wiedergutmachung archival materials into digital humanities infrastructures and lays the groundwork for future knowledge graph generation, ontology validation, and the incorporation of additional historical entities and uncertain temporal and spatial information. The ontology is available on https://github.com/ISE-FIZKarlsruhe/bzko.
Read the full abstract

All authors Dilek Yargan, Jörg Waitelonis, Mahsa Vafaie, Harald Sack

2608.06918 · 7 Aug · 13 pages, 4 figures, accepted to Ontology Showcase at the 16th International Conference on Formal Ontology in Information Systems (FOIS 2026), to be published in Proceedings of the Joint Ontology Workshops (JOWO) - Episode XII: The Tropical Spring of Ontology, co-located with the 16th International Conference on Formal Ontology in Information Systems (FOIS 2026)

Abstract PDF

Information Retrieval · Cross-listed from cs.CL

Georeferencing Non-Gazetteered Place Names using Biological Specimen Records

Aneesha Fernando, Surangika Ranathunga, Kristin Stock et al. (+2 more)

Biological specimen records collected by natural history institutions constitute a rich source of temporal geographic knowledge, capturing biodiversity information about regional landscapes as they were recorded at different times. Using digitised data from the Allan Herbarium (New Zealand), this study identifies place names in these specimen locality descriptions that are absent from current gazetteers; we refer to these as non-gazetteer place names (NGPs). These place names are typically historical, vernacular, or colloquial and were used as landmarks to describe a specimen's location at the time of collection. We then investigate the problem of georeferencing the NGPs using only the limited information available in the specimen records. To resolve this, we leverage repeated occurrences of the same place name across specimen records with different specimen locations and spatial relation terms, extracting and inverting these relations to derive constraints on NGP locations. This approach is instantiated within deterministic, probabilistic, and LLM-based methods, enabling a comparative analysis of their strengths and limitations for text-based spatial inference. On a pseudo-NGP benchmark, probabilistic inference achieves the highest accuracy (median error 1.43 km; A@1 km 36%), while the LLM yields competitive but less precise estimates (median error 1.80 km; A@1 km 31%), indicating that, despite advances in LLMs, traditional modelling remains advantageous when high spatial precision is required.
Read the full abstract

All authors Aneesha Fernando, Surangika Ranathunga, Kristin Stock, Raj Prasanna, Christopher B. Jones

Information Retrieval

Rhetorical-Role-Aware Retrieval-Augmented Generation for Legal Question Answering over Indian Supreme Court Judgments

Sayed Ayaan Ahmed Sha, Sangeetha Sivanesan, Anand Kumar Madasamy et al. (+1 more)

This research paper proposes a Retrieval Augmented Generation (RAG) framework that is specific to the legal field in order to assist interactive retrieval and reason about judgments from the Supreme Court of India. The solution uses an enhanced version of RAG framework which consists of rhetorically based chunking, fusion-based retrieval, and cross encoder reranking methods to increase the relevancy of the information retrieved. In order to improve conversations, the proposed framework uses chat history along with query classification and rewriting in order to understand user intention from successive queries. Additionally, there are features that take into account structural aspects of legal documents, such as isolated names of judges that could have an impact on retrieval quality. The evaluation was done using the DeepEval framework and demonstrated strong performance on metrics including contextual recall and answer relevancy, which proves that the framework is very effective in dealing with legal question-answering tasks that require a lot of context. The results emphasize the importance of domain specific enhancements in developing legal AI systems that are both reliable and explainable.
Read the full abstract

All authors Sayed Ayaan Ahmed Sha, Sangeetha Sivanesan, Anand Kumar Madasamy, Navya Binu

Information Retrieval

Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training

Oseong Choi, Hoeinn Kim, Jihoon Lee et al. (+2 more)

Foundation model(FM) for recommendation has shown strong ability to model long-horizon sequential user behavior. In practice, a single pretrained foundation model is often adapted to diverse downstream serving surfaces through Supervised Fine-Tuning(SFT). However, optimizing task-specific objectives such as clicks or likes does not necessarily align the serving policy with the business metrics that determine recommendation quality. We propose a three-phase progressive post-training framework that explicitly separates downstream adaptation from business-metric alignment. The adaptation stage is decomposed into Linear Probing(LP) and Full Fine-Tuning(FFT): LP first stabilizes randomly initialized downstream heads within a frozen pretrained representation space, and FFT then jointly specializes the full model for the target task. On top of this stabilized policy, Reinforcement Fine-Tuning(RFT) aligns the model with practical business objectives using a learned reward model. Rather than directly optimizing the serving policy on sparse business targets, we train the policy on dense implicit feedback and use business-metric supervision only for reward modeling. Offline experiments show that the progressive LP-FFT-RFT framework outperforms single-phase alternatives, and that reward-based alignment yields a stronger serving policy than directly using the reward model itself for ranking. Large-scale online A/B tests further show that the proposed framework improves production recommendation quality over a conventional non-foundation baseline. A reference implementation is available at https://github.com/webtoon/rec-fm-progressive-alignment
Read the full abstract

All authors Oseong Choi, Hoeinn Kim, Jihoon Lee, Byungsoo Kang, Taeyeong Jang

Thursday 6 August

Information Retrieval

Financial Evidence Crowding: Diagnosing and Mitigating Constraint-Induced Displacement in Retrieval-Augmented Generation

Yixi Zhou, Jiayi Yin, Fan Zhang et al. (+2 more)

Retrieval-augmented generation (RAG) retrieves candidate evidence and sends only a limited top-ranked subset, the top-k context, to a generator. In financial question answering, passages can match a query's topic while conflicting with its period, segment, metric scope, or table scope. We study the resulting set-level ordering failure, which we call financial evidence crowding. FinDeCrowd-Stress isolates this failure through matched compatible and incompatible candidate pools while fixing the query, relevant evidence, ranking model, candidate count, and retrieval budget. On a FinDER test split containing companies unseen during training, incompatible pools reduce top-10 evidence inclusion (Recall@10) by 0.147 relative to equally difficult compatible pools. This gap shows that conflicting candidates consume limited context slots and displace answer-supporting evidence. We then introduce FinDeCrowd-RAG, a learned score correction that combines a fixed relevance score with typed compatibility and local lexical competition. A query-level identity gate applies the correction only when it predicts a better order; otherwise, it preserves the original ranking. On identical controlled candidates, FinDeCrowd-RAG raises top-10 evidence inclusion from 0.757 to 0.902 by recovering evidence already present in the candidate set. On a FinDER index built without query-specific candidate insertion, gated reranking raises this inclusion rate from 0.420 to 0.492, while top-100 retrieval coverage remains 0.743 by design. With a fixed generator, the same ordering change improves answer accuracy and citation recall on FinanceBench and FinQA. These results identify constraint-induced displacement as a measurable RAG evaluation target and show that identity-gated reranking can recover evidence already covered by first-stage retrieval.
Read the full abstract

All authors Yixi Zhou, Jiayi Yin, Fan Zhang, Xiangyi He, Haipeng Zhang

Information Retrieval · Cross-listed from cs.CL

Pre-Inference Routing for Cost-Efficient Document Field Extraction

Sreerekha Rajendran

Most document-extraction systems use a single model for all documents. This is simple but can be costly for easy cases and less effective for difficult ones. We examine whether we can predict a document's difficulty before extraction using inexpensive, document-based signals, and use this to choose between a cheaper and a stronger extractor. We find that routing only helps if two conditions hold: the cheaper model fails often enough to make routing worthwhile, and those failures can be predicted from visible features such as image quality and layout. We turn these into a practical test and apply it to five genres. When both conditions are met, the calibrated router reduces cost by 31-33% on receipts and 77% on degraded ad-buy forms while keeping quality within 0.02 F1 of always choosing the large model. Routing does not help if either condition is missing, as with clean digital invoices or nutrition labels that are already easy to read. A small labeled pilot can predict whether routing will work, and in the two cases where we ran it first, the prediction was correct. A simple bag-of-words router works about as well as engineered features, showing that the main limit is the genre, not the router design; we use interpretable features to help explain which genres can be routed. The router must be retrained for each dataset and does not transfer across datasets, even within the same genre. These results hold for two model pairs with cost differences of 5x and 3x.
Read the full abstract

Information Retrieval · Cross-listed from cs.AI

Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations

Sagar Tamang, Ayush Vyas and Tabarakul Hazarika

Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbours of the query. We argue that for an important class of documents – financial statements, audit reports, regulatory returns – this design is structurally unsound, and we make the argument measurable. On a 780-page government financial report, 86.8% of content lines are table rows, thousands of near-identical figures compete in one embedding space, and a figure inherits its unit from a header a median of 13 lines above it – so a chunk boundary routinely separates a number from whether it is in lakh or crore, an error of two orders of magnitude. A table-aware chunker built as a steelman fixes the unit problem but leaves 27-30% of numeric chunks with no fiscal-year header at every chunk size we tried. We propose READ (Reliable Embedding-free Agentic Document-search), in which an agent reads the raw document through three deterministic operations – normalized lexical search, structural navigation, and bounded span reads – exposed over the Model Context Protocol, so a trajectory is a replayable audit trail, not an opaque similarity score. On 51 verified questions READ answers 58.8% against dense retrieval's 15.7% (p_Holm = 2 x 10^-5) – or 35.3% tuned, which READ still leads by 23.5 points (p_Holm = 0.017). An agent given the same loop but a top-k tool reaches only 27.5%, locating the gain in the interface rather than in iteration. We also report what the evidence does not support: BM25 is statistically indistinguishable from READ, so our result separates embedding-based from embedding-free retrieval, not agentic from lexical search.
Read the full abstract

Information Retrieval

Gryphon-v2: One Model in Place of a Cascade - Generate-and-Rank Recommender with Rollout Distillation

Anna Lipkina, Daria Tikhonovich, Viktor Yanush et al. (+6 more)

Industrial recommender systems are commonly deployed as multi-stage cascades with separate candidate generators, pre-rankers, and final rankers. Although effective, these cascades require repeated user-history processing, complex feature pipelines, and multiple serving stages. Semantic-ID-based generative retrieval offers a path toward simpler end-to-end systems, but next-item prediction alone does not capture the fine-grained preferences encoded by production ranking objectives. We present Gryphon-v2, a unified generate-and-rank architecture for end-to-end recommendation. The model encodes a user history once, generates Semantic-ID candidates with an autoregressive decoder, resolves them to catalogue items, and ranks them with an item-level Ranking Module that reuses the shared encoder states. To transfer fine-grained production ranking preferences without adding an expensive second model to the serving path, we distill a high-capacity, training-only Teacher Ranker into the Ranking Module. Gryphon-v2 is trained with Rollout Distillation: teacher scores are the only ranking supervision, and they are collected over two complementary candidate distributions. Rollouts from the current decoder expose the Ranking Module to candidates produced by the same generation mechanism used at serving time, while logged impressions cover items users were actually shown. In an online A/B experiment on a large-scale recommendation surface at Yandex Music, a single Gryphon-v2 model replaces a production cascade comprising more than 15 candidate generators, pre-ranking, and final ranking. The deployment increases the number of active users by 1.41% at serving latency comparable to the production cascade. These results support the practical viability of a generative retriever with a Ranking Module distilled from the Teacher Ranker as an end-to-end alternative to a production cascade.
Read the full abstract

All authors Anna Lipkina, Daria Tikhonovich, Viktor Yanush, Mariia Ulianova, Oleg Sorokin, Vladislav Dodonov, Ilya Murzin, Denis Burshtein, Nikolay Savushkin

Information Retrieval · Cross-listed from cs.HC

"I don't know anything about laptops!" - User Perception of Digital Product Advisors Adapting to Their Knowledge Levels

Kevin Schott, Andrea Papenmeier, Daniel Hienert et al. (+1 more)

Conversational commerce uses digital assistants to support the search process and decision-making in e-commerce. Effective communication in these interactions can be facilitated by assistants adapting their communication style to users and supporting shared understanding. An open challenge in this context is adapting the presentation of complex product information to users with varying levels of domain knowledge. To investigate strategies for such knowledge-level adaptation, we set up a chatbot-assisted laptop search scenario. In a between-subjects experiment (n = 251), we examined novice and expert perceptions of product attribute recommendations presented as technical information only (T), or augmented with performance categories (TC), attribute explanations (TE), or both (TCE). For novices, approaches with explanations (TE, TCE) were perceived as more helpful and led to higher perceived learning than those without. Novices also rated the combined approach (TCE) more appropriate than the baseline (T) and TC in terms of information quantity, indicating that explanations are crucial to understand and benefit from performance categories. Critically, experts showed no significant differences across conditions, suggesting that providing supplementary information beneficial to novices did not detract from their experience. We distill these findings into four concrete design guidelines for inclusive text-based product advisors in technical domains: use TCE by default; keep a single inclusive interface; avoid standalone categories; and support user agency and personalize to the stated use case.
Read the full abstract

All authors Kevin Schott, Andrea Papenmeier, Daniel Hienert, Dagmar Kern