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

Thursday 20 August

Information Retrieval · Cross-listed from cs.AI

From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG

Zlatan Feric, Amir Taherin, Yanzhi Wang et al. (+1 more)

Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache footprint, memory traffic, latency, and energy. Context compression offers a natural remedy by pruning retrieved text before generation. However, state-of-the-art context-compression methods are typically used with a fixed compression budget, or with the rate selected offline and then applied at inference time. This static view ignores both workload variation and the live state of the edge device. On an edge SoC, compression is not free: the compressor itself runs on the same SoC and consumes latency and energy that can offset any generation savings. This paper proposes a vision for telemetry-informed adaptive compression in edge RAG, grounded in experimental evidence. We characterize the compression tradeoff on the NVIDIA Jetson AGX Thor using Llama and Qwen generators, Natural Questions and HotpotQA datasets, and LLMLingua-2 compression. Our measurements show that generation dominates the RAG budget for larger models, reaching roughly 90% of per-query latency and 91% of GPU energy for 7B-8B generators. Exploring the impact of the compression rate reveals an adaptive operating region: mild compression can miss energy opportunities, and overly aggressive compression can hurt inference quality. Intermediate compression can reduce GPU energy by up to 53.2%, and SoC energy by up to 48.2%, with negligible quality loss. We argue for runtime policies that dynamically manage compression, guided by workload features and edge telemetry.
Read the full abstract

All authors Zlatan Feric, Amir Taherin, Yanzhi Wang, David Kaeli

Information Retrieval · Cross-listed from cs.CL

Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)

Pranav Chandaliya

Stock market analysts and investors face a daily challenge: too much financial news, too little time. Manually reading and synthesizing hundreds of company-specific articles is impractical, yet missing key information can directly affect investment decisions. This project, conducted at George Washington University in Fall 2023, explores whether Large Language Models can automate this process reliably. We built a pipeline that pulls news articles from the News API, company background from Wikipedia, and stock price data from Yahoo Finance for ten major companies (AAPL, MSFT, GOOGL, AMZN, META, TSLA, JPM, NVDA, WMT, DIS). Because LLMs cannot directly process numerical tables, we developed a simple but effective template that converts stock data into natural language narratives. We then tested two summarization approaches (Summarize Chains and Retrieval-Augmented Generation with FAISS) across three open-source models (Falcon-7B-Instruct, DistilBART-CNN-12-6, BART-Large-XSum) for news, and GPT (text-davinci-003) for stock summaries. Falcon-7B with Summarize Chains gave the best results, covering all news events accurately and coherently. RAG, while promising in theory, caused severe repetition in Falcon and hallucinated facts in BART-Large when k was large. Both LLM-based approaches outperformed a simple Lead-3 baseline on ROUGE-1. We also built a Streamlit dashboard for interactive stock visualization. The work was done in Fall 2023, before RAG-based financial tools became widespread, and the failure modes we document, particularly hallucination under RAG in smaller models, remain relevant today.
Read the full abstract

Wednesday 19 August

Information Retrieval

Query Implied Generative Engine Optimization

Shilpa Ramakrishna and William B. Andreopoulos

The landscape of search has changed drastically with how people look for information online. Traditional search engines are being replaced by Generative Search Engines (GSEs), which use Large Language Models (LLMs) to generate natural language responses to user queries. For content creators, visibility is no longer solely determined by ranking in search results but by being cited within generated responses. But Generative Search Engines are black-boxes, leading to the emergence of Generative Engine Optimization (GEO), a set of techniques aimed at improving content visibility in generative search settings. Most existing approaches rely on the explicit queries or query derived signals to align content to better suit user needs. We propose Query Implied Generative Engine Optimization (QI-GEO) to infers user intent directly from the document. Our approach approximates document's intent space and identifies content that may be missing yet relevant to answer potential user queries. Evaluation on GEO-Bench and Extended GEO-Bench demonstrated improvements across objective and subjective metrics. QI-GEO improved objective scores by up to 15.9% and subjective scores by up to 17.6%, while yielding nearly twice as many citation gains as citation losses. These results suggest that document-derived approximations of user intents can improve visibility without relying on explicit query inputs.
Read the full abstract

Information Retrieval · Cross-listed from cs.DL

A Pathway for Assessing Grey Literature: Leveraging AI to Extract Conference Metadata and Organiser Information from Calls for Papers

Angelo Salatino, Francesco Osborne, Alexis Vizcaino et al. (+2 more)

Despite its importance, grey literature, including Calls for Papers (CfPs), remains largely overlooked in Metascience and Scientometric analysis due to its unstructured, highly heterogeneous format, which traditional tools struggle to process at scale. However, Large Language Models now offer a pivotal opportunity to devise innovative tools for systematically harvesting and processing such data. In this paper, we introduce COCI, an AI-based framework that automates the extraction of granular, structured metadata from raw CfP text. COCI employs a multi-stage pipeline for entity extraction, followed by author disambiguation against OpenAlex and semantic mapping of topics and conference series. This process identifies key data points, including conference editions, geographic locations, and comprehensive lists of organisers, along with their specific roles and affiliations. By structuring this previously inaccessible information, COCI establishes a foundation for the systematic analysis of grey literature, enabling new research opportunities and shifting the scholarly focus towards non-publisher-based events.
Read the full abstract

All authors Angelo Salatino, Francesco Osborne, Alexis Vizcaino, Aliaksandr Birukou, Enrico Motta

Information Retrieval

HARP: Hierarchical Adaptive Ranking with Preference-Adaptive Fusion for Query-Based CVE Prioritization

Haochen Liu, Zhengzhang Chen, Haoyu Wang et al. (+3 more)

Vulnerability prioritization is inherently preference dependent, since the same CVE can receive different remediation priority under different operational preference scenarios. Existing scoring systems and ranking methods typically assume a fixed criterion. In practice, organizations already operate under a preference scenario, but this preference is often implicit and difficult to express as a written prompt instruction, while triage queries usually do not encode it. Past validated triage cases under the current scenario are more readily available. We study query-based CVE prioritization in this setting and propose HARP, a graph-grounded multi-view framework that ranks candidates from a natural-language query together with a support bank of historical labeled examples from the current preference scenario, without requiring an explicit textual summary of that scenario. HARP retrieves evidence from a vulnerability knowledge graph, scores candidates with policy-conditioned global, enterprise, and user views, and fits view-fusion weights from sampled supports. Experiments across three preference scenarios and multiple backbone LLMs show that HARP outperforms multiple baselines, expressing our method's effectiveness.
Read the full abstract

All authors Haochen Liu, Zhengzhang Chen, Haoyu Wang, Yanchi Liu, Jundong Li, Haifeng Chen

Information Retrieval

Quantization Beyond Uniform Bit Allocation

K. S. Sreeramji, Sabyasachi Basu, Ravishankar Krishnaswamy et al. (+2 more)

Quantization is a fundamental technique to handle the growing sizes of embeddings generated by modern models. Existing quantization schemes are largely embedding agnostic and allocate bits uniformly across dimensions. However, recent models produce embeddings with significant geometric structure. In this work, we investigate whether a variable bit allocation scheme can improve quantization quality under a fixed memory budget. We propose a simple variable bit allocation framework that partitions an embedding into contiguous buckets and allocates storage non-uniformly across them. Using a greedy allocation strategy, we instantiate this framework for both Product Quantization (PQ) and Scalar Quantization (SQ). We perform a series of experiments on embeddings known to have the Matryoshka property (MRL), and consistently observe that non-uniform allocations outperform uniform baselines at identical storage budgets. The largest improvements occur in the low-bit regime, where uniform allocation is particularly inefficient for MRL embeddings. At the same compression rates, variable allocation improves recall by up to 8% for PQ and up to 18% for SQ. Our results suggest a new direction for structure-aware compression and indexing techniques for large-scale retrieval systems.
Read the full abstract

All authors K. S. Sreeramji, Sabyasachi Basu, Ravishankar Krishnaswamy, Kirankumar Shiragur, Yujia Wang

Information Retrieval · Cross-listed from cs.SD

Finetuning Strategies for Querying Sounds by Vocal Imitation

Aditya Bhattacharjee, Christos Plachouras, Sungkyun Chang et al. (+1 more)

This technical report describes our winning submission to the AES AIMLA 2025 Challenge on querying sound effects by vocal imitation. We investigate two complementary fine-tuning strategies: contrastive learning with a frozen, pretrained CED encoder, and joint contrastive-triplet learning with semi-hard negatives using a MobileNetV3 encoder. This report has been updated for posterity to include details released after the challenge.
Read the full abstract

All authors Aditya Bhattacharjee, Christos Plachouras, Sungkyun Chang, Emmanouil Benetos

Information Retrieval

rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation

Minh Hoang Nguyen, Tung Le and Huy Tien Nguyen

Large language models can improve recommendation quality by reasoning explicitly over user history and candidate items - for example, extracting a user's preferences or explaining why one item fits better than another - rather than mapping history directly to a ranked list. This reasoning, however, is expensive to repeat on every ranking request and, once produced, is typically consumed once and discarded, leaving it neither reusable across future requests nor easy to inspect or correct as user tastes drift. Our insight is that reasoning does not need to be regenerated at every call if it can instead be compressed once into a compact, structured memory that a lightweight model retrieves from. We propose rEDMRec, which distills a teacher LLM's reasoning into four typed, editable experience channels - long-term preference, short-term context, item-perception, and counterfactual hard-negative comparisons - maintained by an LLM memory controller that performs Add/Delete/Modify/Keep operations and refines entries via K-agent debate. A lightweight student LLM then ranks candidates purely by retrieving from this memory, without invoking the teacher again, decoupling online inference cost from reasoning depth. Across ML-1M, Amazon Beauty, and Steam and ten student backbones, rEDMRec improves HR@1 over zero-shot, few-shot, and RAG on every backbone, and over GraphRAG on most backbones, with Impv up to 13.3% vs. the second-best baseline on ML-1M. Channel ablations show that short-term context is the only channel that helps consistently across capacity tiers, whereas long-term, item-perception, and counterfactual contributions are capacity-dependent (and can reverse on the strongest students); debate-based memory optimization lowers bank duplication by 7.4 percentage points while raising downstream HR@1 by up to +0.029 over six optimization epochs.
Read the full abstract

Information Retrieval

Think-to-Personalize: Unifying Reasoning and Retrieval for User-Centric Personalized Dense Retrieval

Angqing Jiang, Gaoming Zhang, Jianchun Song et al. (+4 more)

Dense retrieval has become a cornerstone of modern local-lifestyle e-commerce search by encoding queries and items into semantic embedding spaces. While recent advancements have transitioned from BERT-based embedding models to Large Language Models (LLMs), most approaches still treat LLMs as static text encoders, neglecting their inherent reasoning capabilities. Furthermore, standard dense retrieval models remain query-centric, which is insufficient in e-commerce scenarios where sparse and ambiguous queries create an intent gap that can only be bridged by the rich context of user history. Meanwhile, existing personalized retrieval methods typically rely on implicit embedding interactions, which lack the reasoning capability to effectively disambiguate user intent from noisy historical behaviors. To address these challenges, we propose Think-to-Personalize (TTP), a novel framework that unifies explicit user-centric intent reasoning with dense retrieval. By reasoning over the user's historical purchase sequence, TTP explicitly deduces latent personalized needs and generates an intent-enhanced query, which is then encoded into a unified dense embedding. Specifically, we design a two-stage training paradigm: (1) a Supervised Fine-Tuning (SFT) stage that establishes cold-start capabilities; and (2) a Reinforcement Learning (RL) stage that aligns the reasoning process with retrieval utility using Group Relative Policy Optimization (GRPO). Extensive experiments on both proprietary and public benchmarks demonstrate that TTP significantly outperforms state-of-the-art baselines. Furthermore, in online A/B tests, it achieved a +0.46% lift in order volume, validating its practical effectiveness and establishing a new paradigm for reasoning-driven personalized dense retrieval.
Read the full abstract

All authors Angqing Jiang, Gaoming Zhang, Jianchun Song, Kena Qi, Dayao Chen, Wei Lin, Defu Lian

Information Retrieval

SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation

Jiandong Ding, Huijie Qin, Tiandeng Wu et al. (+1 more)

Semantic ID tokenizers assign code sequences to catalog items, which generative recommenders predict and resolve back to items. Reusing a released mapping requires checking its code organization, item resolution, and compatibility with an existing model after a refresh. SIDScope provides these checks through source traced adapters, mapping diagnostics, candidate retrieval tests, and generated trace analysis. Its inventory contains nine exports from seven tokenizer families across Amazon and Yelp, including eight executable routes and one auditable snapshot. The analyses establish three distinctions. First, code allocation and item addressability differ: in GRID, tail items occupy 95.7 distinct codes per 100 items, yet only 82.2 percent have globally unique codes. Second, prefix alignment calibrates retrieval operations that use prefixes. With fixed candidate budgets and ranking, original assignments on Beauty and Instruments expose more targets than controls preserving code capacity and coarse popularity. Resolving identical generated paths also shows that an explicit item selection rule recovers part of the gap between target path survival and singleton credit. Third, a released refresh repairs missing codes, while model adaptation separately restores new item recall. SIDScope supplies code, diagnostic summaries, and verification tools to compare mappings, evaluate their use in retrieval and generation, and test model reuse after changes.
Read the full abstract

All authors Jiandong Ding, Huijie Qin, Tiandeng Wu, Yi Cao

Information Retrieval

GateDiffInt: Gate-Mediated Controllable Diffusion and Multi-Intent LLM Distillation for User Behavior Modeling

Jialong Duan, Zichen Zhang, Zirui Tu et al. (+7 more)

Existing ranking models encode intent only implicitly, making it hard to disentangle structured intents of varying strength and temporal scale. Noise and intent in behavior sequences are mutually reinforcing—we call this Noise–Intent Coupling (NIC). Noise dilutes true intents, while the lack of structured intent priors leaves denoising without a clear target. To address NIC, we propose GateDiffInt, an intent interaction framework for industrial ranking. It uses the final conversion signal to jointly align sequence denoising and intent extraction. GateDiffInt applies a controllable forward diffusion process with dual gating to enhance and denoise behavior sequences. A large language model then acts as teacher to distill four structured intents—long-term, short-term, latent, and conversion into a lightweight student model. The enhanced sequence and structured intent representations are deeply fused via attention to produce intent-aware representations for conversion-rate prediction. Extensive experiments on public and large-scale industrial datasets show consistent gains over strong baselines. In online A/B tests serving hundreds of millions of daily active users, GateDiffInt delivers substantial GMV improvements and has been deployed to primary traffic, confirming both effectiveness and production readiness.
Read the full abstract

All authors Jialong Duan, Zichen Zhang, Zirui Tu, Zheng Zhang, Zepeng Li, Qingyao Cui, Qinwen Wang, Yudan Liu, Luo Yang, Yao Hu

Information Retrieval

GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval

Ernest Beta, Odysseas S. Chlapanis, Dimitrios Galanis et al. (+1 more)

Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public retrieval benchmark derived from, and complementing GreekBarBench, which did not include retrieval. The new benchmark comprises 283 bar-exam questions, each accompanied by the facts of the case it refers to, and 6,308 candidate statutory articles to retrieve from. Questions and facts are stated in everyday language, but need to be mapped to the formal terminology of statutes and their abstract legal concepts. A further complication is that not all of the case facts are relevant to each question of a case. Experimenting with three BM25 variants and nine dense retrievers, we find that vanilla dense retrieval far outperforms vanilla sparse retrieval in Recall@100. However, LLM-based query reformulation helps BM25 close that gap, while also improving dense retrieval. With a ten-round ReAct-like LLM reformulation loop that we introduce, BM25 improves further in Recall@100 and obtains the best nDCG and MAP scores of all tested retrievers. Query reformulation also outperforms pseudo-relevance feedback, sparse-dense fusion, and English translation.
Read the full abstract

All authors Ernest Beta, Odysseas S. Chlapanis, Dimitrios Galanis, Ion Androutsopoulos

Information Retrieval · Cross-listed from cs.LG

Visual-Aware Representation of Web Pages for Machine Learning Applications

Radek Burget and Radek Hranický

Applying machine learning to web pages is challenging due to the need to interpret HTML together with associated resources and perform rendering to obtain a meaningful visual and layout-aware representation. As a result, machine learning over web content remains comparatively underexplored. In this paper, we present a platform for visual-aware representation and machine learning over web pages based on the open-source rendering tool FitLayout. The platform provides a server capable of rendering web pages, explicitly capturing their visual and structural properties in an RDF-based representation, and persisting the rendered documents in an integrated storage. The processing pipeline is controlled via a REST API, while SPARQL queries are used to retrieve structured data suitable as input for machine learning algorithms. By explicitly modeling rendered web pages, including fine-grained layout details, the platform enables dataset sharing and supports the reproducibility of experimental results. The architecture supports the complete dataset preparation workflow, from web page collection and rendering through preprocessing and annotation of content elements to downstream learning tasks. We further provide a Python client library that integrates the platform with standard machine learning workflows. As a demonstration, we show how rendered web pages can be transformed into graph-based representations and used to train graph neural networks for recognizing key content elements, illustrating both the applicability of the approach and the reproducibility of the results.
Read the full abstract

Information Retrieval · Cross-listed from cs.CV

Composed Historical Image Retrieval by Modeling Temporal Representations

Adrià Molina Rodríguez, Oriol Ramos Terrades and Josep Lladós Canet

While time evolves linearly, the geometry of neural embedding spaces is inherently multi-dimensional, often chaotic, and difficult to interpret. In principle, one could constrain an embedding space to a single temporal dimension; however, such a reduction would sacrifice performance on downstream tasks, as one-dimensional embeddings cannot retain sufficient expressive capacity. This paper asks whether it is possible to learn representations that preserve temporal structure while remaining effective for image and object retrieval, and answers this question by building the mathematical foundations of such a system. We propose Temporally Decomposable Image Representations (TDIR), a representation learning algorithm that decomposes historical photographs into separate date and content components through orthogonal subspaces. We define and prove the conditions under which such a decomposition is achievable, characterize the error incurred when those conditions are only partially met, and show that orthogonality between temporal and categorical subspaces emerges naturally from the joint optimization, without requiring it to be imposed explicitly. Beyond its geometric properties, TDIR enables a class of transitive operations on embedding spaces: the temporal information of one image can be extracted and injected into the representation of another, with no label supervision required. All theoretical properties are grounded and validated in the real-world problem of Composed Image Retrieval on historical photographs, where a query simultaneously specifies object content and a target time period, either through labels or through example images. This in-the-wild setting serves as a concrete backing for the propositions we derive, offering an intuitive and interpretable way to navigate photographic archives while maintaining competitive performance in both date estimation and object retrieval.
Read the full abstract

Information Retrieval

PILOT Technical Report

Jiuning Lin, Ruiquan Lan, Xiaodong Zhu et al. (+17 more)

Existing agentic approaches for recommendation system optimization remain fundamentally reactive: they adjust parameters in response to observed metric changes but lack the ability to proactively design controlled experiments, personalize strategies at the user-segment level, or accumulate reusable experimental methodology across tasks. We present PILOT (Proactive Insight Learner for Online Tree-Experiments), an LLM-agent framework that organizes three roles within a constrained control loop where deterministic services enforce all safety, statistical, and permission boundaries: (1) an Experiment Manager that drives the full experiment lifecycle – task intake, observation governance, anomaly recovery, and postmortem – by selecting only from a rule-generated legal-command envelope; (2) a Search Planner that proposes candidate decision trees for user-segment-level personalization, invoked only when the Manager requests planning; and (3) a Memory Curator that asynchronously distills experiment outcomes into strategy-level domain knowledge and provenance-tracked methodology, failure-isolated from the main loop. The Manager makes the agent proactive, the Planner enables population-level personalization beyond global tuning, and the Curator turns every completed task into a learning opportunity for the next. Deployed on Taobao's platform with 5 experimental buckets, PILOT is compared against ROAM(Reactive Optimization with Agent-driven Moves), a free-exploration agent without lifecycle governance or structured hypothesis testing. PILOT achieves up to +1.40% IPV, +1.60% Core IPV, +0.96% transaction count, and +1.50% transaction amount, improving over ROAM's best results (+1.00% IPV, +0.90% Core IPV, +0.60% transaction count, +1.13% transaction amount) while raising search efficiency from 53.3% to 93.3% (+40 pp), with no human intervention throughout the experimental cycle.
Read the full abstract

All authors Jiuning Lin, Ruiquan Lan, Xiaodong Zhu, Bin Zhang, Chengyu Lai, Chuxin Chen, Dimin Wang, Han Zhu, Hongtao Cheng, Jialin Zhu, Lingqing Zhang, Shuai Zhong, Tao Wang, Weipeng Huang, Yinjiang Cai, Yinnan Song, Yuan Liu, Zhibo Xiao, Zhixin Ma, Zihong Huang

Information Retrieval

OneModel: A Unified Foundation for Platform-Scale Multi-Scenario Ranking

Yinqi Zhang, Peiyu Hu, Yuntian Tang et al. (+16 more)

Platform-scale recommender systems often span multiple business streams such as organic recommendation, advertising, and merchant services, where user behaviors form a continuous cross-stream trajectory. Maintaining separate ranking systems fragments user representations and increases engineering cost. We propose OneModel, a unified framework for multi-stream final ranking. OneModel maps heterogeneous behaviors into shared event sequences, learns long-context user representations with an action-oriented backbone, and introduces Scenario-aware Information Modulation to balance cross-stream transfer and stream-specific specialization. For production deployment, OneModel further adopts stratified user representation, multi-objective training, and optimized online serving with feature decomposition, user feature prefetching, shared user-tower computation, and graph-level inference optimization. We deploy OneModel in production at Xiaohongshu, where it delivers consistent offline gains over strong baselines and scales favorably with context length and model capacity. Online A/B tests improve Time Spent by +0.33% and Engagement by +1.25% in Explore Feed, lift advertising value by +3.43% and CTR by +8.18% in Feed Advertising, and raise DGMV by +1.1867% and GPM by +2.1585% in Merchant Recommendation, validating unified multi-stream ranking as an effective production foundation.
Read the full abstract

All authors Yinqi Zhang, Peiyu Hu, Yuntian Tang, Siying Gu, Jiahao Liang, Longxin Kou, Haiqing Hu, Shuman Zhuang, Yubin Xu, Chenggen Sun, Bin Ye, Donghui Xu, Zhaoyu Liu, Jiang Rong, Yuting Jia, Zhaokai Luo, Leilei Ma, Yiying Xie, Yao Hu

Information Retrieval · Cross-listed from cs.AI

FinRCA-Bench: Benchmarking Evidence Retrieval and Reasoning for Financial AI Systems

Pratik Ghawate

Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive the right evidence. In financial reconciliation, the evidence needed for diagnosis is distributed across invoices, purchase orders, approvals, allocations, payments, ledger entries, and bank activity, linked by transactional relationships rather than textual similarity. End-to-end accuracy can therefore conflate evidence access with reasoning quality. We introduce FinRCA-Bench, a deterministic synthetic benchmark of 2,250 accounts-payable-to-bank reconciliation cases spanning 14 operational tables, including 1,500 injected failures across 15 causal categories and 750 legitimate or hard-negative cases. Root-cause labels and record-level evidence contracts are hidden from the model, allowing retrieval to be evaluated independently of answer correctness. We compare Rules/SQL, classical machine learning, dense semantic retrieval, deterministic relational expansion, and Typed Provenance Graph Retrieval (TPGR), a typed traversal restricted to persisted transaction relationships. Rules/SQL reaches 84.97% held-out exact accuracy and classical ML reaches 95.44%. Holding the reasoning model, prompt, and generation settings fixed while changing only retrieval increases macro required-record recall from 0.83% to 77.70% and exact 16-class accuracy from 2.05% to 72.44%. Structural retrieval failures outnumber reasoning failures with sufficient retrieval by 95 to 15; 254 correct predictions occur despite incomplete retrieval, and strict returned-evidence contract accuracy is only 5.72%. On FinRCA-Bench, retrieval architecture strongly shapes observed AI-system performance, and a correct root-cause label is a weak proxy for an auditable diagnosis.
Read the full abstract

Information Retrieval · Cross-listed from cs.HC

Reducing Technician Search Burden: A Multimodal RAG for Cessna 172 Maintenance Manual

Seongjun Ha, Md Rashedul Islam, Gaurav Nanda et al. (+1 more)

Proper use of the aircraft maintenance manual is essential for correct maintenance, providing procedures, diagrams, cautions, and specifications. However, technicians often avoid consulting it because it is difficult to navigate and time-consuming under strict schedules. Retrieval augmented generation (RAG) models have recently been introduced in aircraft maintenance, yet existing models focus solely on textual retrieval. This research therefore targeted the Cessna 172 Maintenance Manual (C172-MM), widely used in general aviation, and developed a multimodal manual retriever (MMR) capable of retrieving multimodal manual pages. Retrieval performance was evaluated using synthetic queries covering procedures, diagrams, caution/safety information, and specifications; the MMR achieved 93.37% recall@5. Beyond retrieval, a multimodal RAG (MRAG) pipeline was examined, in which retrieved pages were input to a vision-language model that generated responses to the synthetic queries, achieving 87.20% semantic similarity to ground-truth answers. Three practical feasibilities were also assessed: inference time, operational cost, and interpretability. Average retrieval time for five pages was 11.93 seconds and response generation took 4.95 seconds, at $0.0091 per query, while interpretability was validated through heatmap visualizations. These results indicate that the MRAG pipeline for the C172-MM can reduce the time technicians spend searching manuals and retrieving multimodal information.
Read the full abstract

All authors Seongjun Ha, Md Rashedul Islam, Gaurav Nanda, Damon Lercel

Information Retrieval

More Context, Same Budget: Dual-Bounded Relational Recall Beyond Top-K Retrieval

Thomson D. Nguy

More context does not require a larger retrieval budget. Under the same ceiling, a retrieval system can recover more of the evidence a question requires by following relationships between evidence that flat top-k ranking leaves behind. We test that proposition with Dual-Bounded Relational Recall (DBRR), which allocates a fixed retrieval budget between relevance-selected seeds and bounded graph-adjacent context, against matched flat top-k retrieval using the same relevance-ranking stage and the same maximum number of retrieval units and tokens. The outcome is complete recovery of the official HotpotQA supporting-evidence set for each question. Across 7,405 FullWiki questions, the Primary DBRR allocation increased complete supporting-evidence recovery by 23.8 percentage points over its matched flat baseline (paired risk difference 0.2377; question-level bootstrap 95% interval 0.2269 to 0.2489). It improved 1,952 questions, tied on 5,261, and harmed 192. Bridge questions drove the effect, with a 28.7-point increase; comparison questions showed a smaller 4.2-point difference. In a prespecified, evaluation-only diagnostic population, real relationships also outperformed random-neighbor and degree-preserving shuffled-graph controls. The result is straightforward: under the same context budget, complete-evidence retrieval depends not only on which items rank highest, but on how context is allocated around them. Relational allocation recovered complete evidence sets that flat top-k retrieval left incomplete.
Read the full abstract

Tuesday 18 August

Information Retrieval · Cross-listed from cs.CL

LabourCrew: A Multi-Agent RAG Framework for Trustworthy Adversarial Deliberation and Statutory Reasoning over Labour Law

Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud et al. (+2 more)

In statutory question answering, every claim must be traceable to evidence, not merely relevant, since unverifiable labour-rights answers carry serious legal consequences. Current systems fall short: single-pass RAG cannot detect insufficient evidence, while multi-agent legal-debate systems treat grounding as a prompting convention, letting agents cite unretrieved evidence. To address this gap, we introduce LabourCrew, a multi-agent RAG framework built around three grounding mechanisms: StatuteGraph, a graph index that explicitly links chapter, section, proviso, and cross-reference structure rather than fixed-length spans; an Evidence Exchange Protocol that confines advocates and an interpreter to an evidence ledger, making citation to unretrieved text impossible, while a fault-tolerant supervisor board runs advocates in parallel so individual failures degrade rather than crash the system; and a Calibrated Trust Gate that replaces categorical accept/reject decisions with a trust score, thresholded via conformal risk control for a distribution-free bound on the false-accept rate. We evaluate on LabourActQA, a 500-item Bangla question set from the Bangladesh Labour Act, 2006, spanning seven reasoning categories and three difficulty tiers. The framework drives the empirical false-accept rate to 0.081, within the target level ($\alpha = 0.10$), achieves the highest Answer Relevancy among HyDE RAG, Graph-RAG, and Hierarchical RAG (0.862 $>$ 0.839, 0.815, 0.828), and degrades gradually rather than catastrophically as question difficulty increases. These results show that calibrated abstention, not retrieval quality alone, is what makes legal question answering auditable in low-resource statutory domains.
Read the full abstract

All authors Fatema Tuj Johora Faria, Mukaffi Bin Moin, Jubayer Al Mahmud, M. F. Mridha, Md. Alam Hossain

Information Retrieval · Cross-listed from cs.CL

Can Large Language Models Identify Meaningful Touchpoints in Conversion Attribution?

Jinqi Wu, Sishuo Chen, Zhangming Chan et al. (+9 more)

Touchpoint selection in conversion attribution, namely identifying meaningful touchpoints contributing to conversions, is essential for e-commerce recommendation and online advertising. Current selection methods rely heavily on collaborative-filtering-based heuristics, which fail to align with user-perceived semantic intent. Through human annotation, we reveal a significant semantic gap: many implicitly-related, semantically relevant touchpoints remain undetected by existing rules. Therefore, we systematically evaluate the capability of Large Language Models (LLMs) in identifying these hidden associations. Our evaluation shows that while LLMs effectively uncover a substantial portion of implicitly-related touchpoints, significant room for improvement remains in their selection performance. Furthermore, we analyze the impact of different prompting strategies and foundation model choices on identification performance, providing valuable insights into their reasoning patterns and effectiveness. These insights offer a new roadmap for transitioning conversion attribution from mechanical rule-matching to human-aligned semantic reasoning. Moreover, we leverage the LLM-attributed conversion labels for enhancing industrial CVR model training and achieve significant offline performance gains, showing the potential of LLMs in conversion attribution.
Read the full abstract

All authors Jinqi Wu, Sishuo Chen, Zhangming Chan, Yong Bai, Chao Yi, Han Zhu, Shuodian Yu, Lei Zhang, Sheng Chen, Chenghuan Hou, Jian Xu, Chaoyou Fu

Information Retrieval

AI in Search Reduces Publisher Referrals Without Improving User Experience: Experimental Evidence

Stephanie T. Wang, Jeffrey Gleason, Yakov Bart et al. (+2 more)

The integration of generative AI into web search delivers synthesized answers to user queries, changing how people navigate and assess information, while raising concerns about the downstream impacts on publishers who supply the underlying content. We conduct a preregistered field experiment (N=1,100) on Google Search, the dominant online search platform, to estimate the causal effects of AI Overviews and AI Mode on user behavior, perceptions, and publisher traffic. We show that removing AI Overviews and AI Mode increases click-through rates to publishers, while an AI Mode-only experience reduces click-through rates and erodes user experience and trust in information found on Google. These findings show that integrating generative AI into web search reshapes online attention, with economic consequences for the online publishers that sustain both search platforms and the overall information ecosystem.
Read the full abstract

All authors Stephanie T. Wang, Jeffrey Gleason, Yakov Bart, Christo Wilson, Danaé Metaxa

Information Retrieval

Multimedia Asset Personalization via Multimodal Embeddings at Netflix

Emma Yanyang Kong, Aditya Deshpande, Bowei Yan et al. (+5 more)

Personalized promotional assets, namely artwork images and video preview clips, are critical to content discovery on Netflix. Traditional models for asset selection rely on ID-based interaction history, leaving them blind to asset content and unable to serve newly launched titles and assets. We describe how multimodal embeddings reshaped production systems at Netflix and report transferable lessons for practitioners adopting foundation-model embeddings into recommender systems. First, pretrained image embeddings unlock cross-title, cross-canvas knowledge transfer. Augmenting a two-tower model with CLIP image embeddings lets a single model serve all five Netflix artwork canvas types, replacing five separately trained per-canvas models and substantially improving cold-start performance. A lightweight extension reuses CLIP's joint text-image space to make artwork personalization query-aware in search. Second, multimodality decisively beats any single modality for video preview personalization. We describe MediaFM, our in-house tri-modal foundation model trained on a large-scale corpus of shots from the Netflix show catalog, fusing visual (SeqCLIP), audio (wav2vec 2.0), and timed-text signals; adopted for video preview personalization, it outperforms strong visual-only baselines both offline and in online A/B tests. Third, a simple offline proxy task whose performance correlates with online outcomes can accelerate the experimentation and productization cycle. Predicting the popularity-based winner from embeddings alone ranks embedding models and versions, pruning the choice space before any end-to-end integration or A/B test; it now gates every new MediaFM checkpoint. We also share the production engineering decisions (shared embedding infrastructure, low-latency serving, cheap screening) that made these deployments viable, along with the design tradeoffs and failure modes we encountered.
Read the full abstract

All authors Emma Yanyang Kong, Aditya Deshpande, Bowei Yan, Asad Abbasi, Santiago Castro, Avneesh Saluja, David Fagnan, Ashish Rastogi

Information Retrieval · Cross-listed from cs.AI

Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application

Elias Schubert and Felix Bießmann

The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While proprietary solutions dominate commercial applications, a rapidly growing ecosystem of open-source Optical Character Recognition (OCR) engines, Large Language Models (LLMs), and Vision-Language Models (VLMs) offers accessible alternatives. However, systematic evaluations on realistic, multi-step extraction pipelines remain scarce. Responsible usage of such extraction tools require comprehensive evaluations on realistic tasks, especially as these solutions will be key components of applications in the public sector that the EU AI act categorizes as high risk. To address this gap we present a comprehensive benchmark assessing the end-to-end performance of open-source systems on a complex real-world document processing task classified as high risk: Student applications for an international study program. We conduct a comprehensive empirical evaluation with state-of-the-art OCR engines, LLMs and VLMs. Our results reveal that while VLMs generally outperform OCR+LLM pipelines, even state-of-the-art open-source models struggle to handle such tasks reliably in zero-shot settings. Only 4 of 35 configurations achieved F1 scores above 0.5, with the best OCR+LLM pipeline matching top VLM performance, though most OCR+LLM combinations performed substantially worse. Roughly 75% of all configurations scored below 0.25. Model scale influences performance, yet the relationship is non-linear: substantially larger models do not guarantee proportionally better results. Input quality, particularly the structural preservation of OCR output, emerges as a critical factor independent of downstream model capability.
Read the full abstract

Information Retrieval

Global Crises and National Policies: A Large Scale Analysis of Political Content in German Language Online Media

Yara Döring and Felix Bießmann

Today most media content is consumed based on algorithmic recommendations. Evidence suggests that this can lead to politically biased media consumption patterns. Automated extraction of political agendas from texts can reveal and analyze political biases in online media – and thus help fostering politically unbiased media consumption. Here we employ modern political text analysis methods demonstrating the potential of automated fine-grained political bias analysis in online media. We conduct an analysis of political content in German language online media during the period 2019–2022, encompassing several million articles and tweets covering events with profound societal impact globally and nationally, the COVID-19 pandemic and the beginning of the war in Ukraine. Our analysis identifies thematic similarity between national (German and Swiss) reporting, particularly for categories driven by international events. We also find divergences emerging in domestically influenced categories, reflecting differences in national policies and institutional structures. A comparison of newspaper and Twitter discourse reveals that both media converge around a shared core during the pandemic, yet differ in intensity and temporal dynamics. Newspapers exhibit more stable political content, while Twitter reacts through short-lived event-driven spikes. These findings indicate that international crises act as a powerful synchronizing force on political content in classical media, temporarily overriding both national and media-form differences. Our automated political analysis empowers citizens by rendering political agendas in online media transparent. This transparency also enables media outlets to bridge the gap between algorithm-driven echo chambers and a more informed, balanced public discourse.
Read the full abstract

Information Retrieval · Cross-listed from cs.AI

Redakto - The Incognito Tab for LLMs

Saurav Kumar Saha, Tom Röhr and Felix Bießmann

Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that personally identifiable information (PII) is removed from any text that enters an LLM. These challenges have become more urgent with novel EU legislation. Uncertainty around LLM usage with respect to privacy concerns in EU countries can be a major blocker for the speed of innovation and transfer from research to applications. Here we present Redakto, a tool that can be used for anonymizing text prior to feeding it to an LLM or other downstream text processing. We provide state-of-the-art functionalities for both redaction of PII but also when used for pseudonymization. These functionalities are exposed such that they can easily be used by end-users, through the Redakto web application, and by developers and researchers, via REST APIs and model context protocol (MCP) hooks. The implementation is fully open source, requires modest compute resources, and can be readily deployed on local hardware. In contrast to prior work and in order to better assess the quality of the anonymized texts, we conduct extensive empirical evaluations on textual data from legal and medical domain with respect to both privacy and utility of the redacted texts. Our empirical results demonstrate that the texts anonymized with different redaction strategies achieve utility scores on par with the original texts, suggesting that anonymization with Redakto can be used for LLM tasks without substantial negative impact for the tasks we explored.
Read the full abstract

Information Retrieval

VisDocAgentBench: Benchmarking Agents for Visually Rich Document Retrieval

Lexiang Hu, Yanzhao Zhang, Mingxin Li et al. (+5 more)

Visually rich documents encode relevance through language, layout, structured visual elements, and corpus context, yet retrieval is typically evaluated by one-shot query–page matching. Agentic-search benchmarks usually score downstream question answering or report generation, leaving document ranking under iterative evidence acquisition underexplored. We introduce VisDocAgentBench, a closed-corpus benchmark comparing static and agentic retrieval under a shared ranked-output contract. It contains 2,375 pages from 100 documents and 120 unique-target queries balanced across direct, one-bridge, and two-bridge evidence structures. Relation-preserving construction yields semantic, relational, and visual queries, followed by full-document review and hard-negative validation. A strong late-interaction visual retriever reaches 97.50% Recall@1 on direct items but 2.50% on two-bridge items, exposing the limits of query–target matching when relevance depends on corpus context. Agents recover much of this loss, but planner choice and retrieval representation remain decisive. Every planner performs better with visual retrieval, whose best R@1 reaches 67.50% versus 37.50% for OCR-text. Ablations identify iterative search and page inspection as consequential capabilities, and providing the complete support context improves ranking on both routes. Trace analysis localizes the remaining losses to target discovery, candidate examination, and evidence-role integration. These findings motivate retrieval agents that combine modality-preserving discovery with evidence-directed verification.
Read the full abstract

All authors Lexiang Hu, Yanzhao Zhang, Mingxin Li, Dingkun Long, Yikang Li, Fuwei Zhang, Yisen Wang, Zhouchen Lin

Information Retrieval

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

Jingyuan Wang, Richong Zhang, Zhijie Nie et al. (+2 more)

Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and retrieval. Existing systems usually rely on prompted expansions, independently trained modules, or staged optimization, leaving generated expansions only indirectly aligned with the retrieval loss that judges them. We train a single decoder-only LLM end to end, where the same model generates the expansion and encodes both the expanded query and candidate documents. This unified setting creates a moving-target problem: retrieval supervision should improve query-side expansion, but the same update also shifts the document embeddings that serve as retrieval targets. We introduce Document Embedding Preservation Tuning (DEPT), which keeps tuned document embeddings close to cached initial embeddings while allowing retrieval gradients to pass through straight-through decoding into the generator. DEPT converts joint query–document movement into query-side adaptation against approximately stable, whitened document embeddings that support index reuse and online hard-negative mining. Experiments with Qwen3-4B-Instruct-2507 and LLaMA-3.2-3B-Instruct on five datasets in BEIR benchmark show that DEPT improves average retrieval quality over training-free, independently trained, and staged unified baselines, while ablations isolate the effects of preservation, whitening, end-to-end expansion training, and online negatives. Code is available at https://github.com/ILSparkle/DEPT.
Read the full abstract

All authors Jingyuan Wang, Richong Zhang, Zhijie Nie, Mingxin Li, Yanzhao Zhang

Information Retrieval

From Student Risk Prediction to SC2R: Semantics-Constrained Counterfactual Recourse for Educational Decision Support

Ngoc Luyen Le, Marie-Hélène Abel and Bertrand Laforge

Learning analytics models can identify students at risk of poor performance, but they do not directly indicate which interventions are feasible, actionable, and compatible with educational constraints. This paper introduces SC2R, a semantics-constrained counterfactual recourse framework for educational decision support. SC2R combines a calibrated predictive model, integer-programming-based recourse generation over discrete action variables, a lightweight RDF vocabulary for intervention-plan representation, and SHACL validation for enforcing timing, budget, immutability, and availability constraints. The framework is evaluated offline on the OULAD dataset using snapshots constructed relative to each assessment at two decision horizons. Results show that the predictive component provides strong performance, that compact intervention plans can be generated at scale, and that semantic validation reveals infeasible plans that lighter optimization-only settings would otherwise accept. Rather than claiming causal improvement in student outcomes, this work shows that counterfactual recourse becomes more operationally meaningful in education when recommendations are not only model-valid, but also semantically feasible and machine-checkable.
Read the full abstract

Information Retrieval

Once Generated, Ranked: End-to-End Generative Slate Recommendation with Unified Semantic-Collaborative IDs

Yang Hu, Jiayi Guo, Jingui Ma et al. (+6 more)

Slate recommendation treats a slate rather than an individual item as the recommendation unit, requiring joint optimization of item interactions and slate utility. Existing approaches typically separate candidate generation from ranking and restrict optimization to retrieved candidates. Generative recommendation with Semantic IDs (SIDs) offers a path to end-to-end recommendation, but existing SID construction often lacks recommendation-aware semantics and effective local collaborative signals, while next-token prediction is misaligned with slate-level objectives. We propose OGR, an end-to-end framework that directly generates ordered slates-"Once Generated, Ranked." OGR first introduces TUSID, which adaptively fuses item-specific semantic and local collaborative information into hierarchical SIDs. It then uses list-wise preference planning and pipelined position-wise SID decoding to model global preferences and inter-item dependencies while generating ordered slates. We further propose SPA, a reward-guided conservative policy optimization method that aligns generated slates with user preferences beyond likelihood imitation. Offline experiments show that OGR outperforms representative baselines, with 48.2% and 27.2% relative NDCG@5 gains on industrial and public datasets, respectively. Online A/B testing on Kuaishou further yields a 1.120% improvement in Effective Views.
Read the full abstract

All authors Yang Hu, Jiayi Guo, Jingui Ma, Ning Li, Jiangling Qin, Yanming Li, Yang Deng, Xiaoshuang Chen, Kaiqiao Zhan