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

Monday 10 August

Information Retrieval

Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation

Guanqun Yang and Wenlong Zhang

Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data loses much of its recommendation accuracy when a modality is unavailable at serving time. We propose Sequential Modality Dropout (SMD): during training, each modality stream (image and text) is independently erased with probability p for an entire user interaction history, so the model learns to predict the next item without relying on any single modality. We measure robustness by retention, the fraction of a model's full-modality accuracy (HR@10) that survives when a modality is removed at test time. Across four backbones (MM-SASRec, IISAN, MISSRec, and fMRLRec) on four Amazon domains, SMD raises text retention by 1.0 to 3.2x at essentially no cost to full-modality accuracy; under an extreme 95% per-item missing rate, it retains 61% of HR@10 versus 22% without (a 2.8x improvement). An optional cross-modal reconstruction loss further lifts retention from 90% to 98% on a simple additive backbone under severe text missingness. SMD is a four-line, architecture-agnostic change that makes multi-modal sequential recommenders robust to the missing modalities they actually encounter in deployment.
Read the full abstract

Information Retrieval

ConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta

Haoyu Han, Yuming Liu, Lei Huang et al. (+3 more)

Modern recommendation systems on social media platforms such as Meta must model complex social relationships, including friendships, group memberships, and creator interactions, alongside massive and heterogeneous content such as text and video. Traditional recommendation models, however, often omit these signals or treat them independently, lacking the reasoning capability to integrate multi-relational context for fine-grained personalization. We present ConnectionMind, a production-ready recommendation framework that tightly integrates the social network structure with large language models (LLMs) to enable scalable, interpretable, and reasoning-aware personalization in Meta. ConnectionMind constructs a heterogeneous graph connecting users, items, friends, groups, and creator pages, and formulates recommendation as a graph reasoning problem: discovering personalized paths from users to candidate items. An LLM-based policy is employed to reason over these graph structures and guide recommendation decisions. To train the system at scale, ConnectionMind adopts a two-stage learning strategy. We first perform supervised fine-tuning (SFT) on large-scale user-item interaction trajectories to initialize the reasoning policy, followed by end-to-end reinforcement learning (RL) to refine the model's ability to reason over social graphs for personalized recommendation. Extensive experiments on multiple real-world datasets demonstrate the effectiveness of ConnectionMind compared to representative baselines. More importantly, ConnectionMind has been deployed in Meta's large-scale recommendation pipeline and has been evaluated through online A/B tests, achieving a 0.43% improvement in video watch time. These results demonstrate measurable real-world impact in a production recommendation system.
Read the full abstract

All authors Haoyu Han, Yuming Liu, Lei Huang, Lizhu Zhang, Jiliang Tang, Xiangjun Fan

Information Retrieval

Listwise Cross-Encoder Fine-Tuning vs. Agentic Instruction Tuning for LLM Rerankers: A Systematic Study in Medical Procedure Reranking

Matan Fainzilber and Shlomit Plavner

Reranking medical procedures against patient queries is a critical component of health insurance information retrieval, complicated by a substantial lexical gap between patient language and clinical nomenclature. We present a systematic comparison of two reranking paradigms for this production task: (1) small cross-encoders (MedCPT, MiniLM-L12) fine-tuned with listwise learning-to-rank objectives across layer freezing configurations, and (2) Qwen3-Reranker-4B, a 4B-parameter instruction reranker whose prompt is iteratively refined via an agentic optimization loop driven by GPT-4.1. On a purpose-built dataset of 2,647 queries across 708 insurance services, we find that a 109M-parameter cross-encoder fine-tuned with ListNet outperforms the 4B-parameter model by 2.6 percentage points on NDCG@3 and 13.3 points on Spearman correlation - at 37x fewer parameters. We report practical findings, a scalable LLM based dataset construction pipeline, and deployment trade-offs relevant to production reranking systems. We release our code and a sample dataset to support reproducibility and adaptation to other domains.
Read the full abstract

Information Retrieval

IntHQ: Task-Interactive Hierarchical Query on Dual-Stream Representations for Generative Recommendation

Junjie Sun, Longfei Xu, Huimin Yan et al. (+3 more)

Multi-task learning over heterogeneous data is fundamental to modern recommendation, while generative models are emerging as the backbone of next-generation recommenders. However, the integration of multi-task learning into the generative paradigm remains largely unexplored. Existing multi-task recommenders, in both discriminative and generative paradigms, extract task-relevant features from a single task-agnostic representation and wire tasks into a predefined conversion funnel. We show that this scheme is inherently prone to a threefold collapse. Source collapse, where task-specific signals are injected late and diluted in the shared latent space. Relational collapse, where task dependencies are either implicitly absorbed by the backbone or statically fixed by predefined funnels. Hierarchical collapse, where tasks depend on features at different scales and shift across training stages. We propose IntHQ, a multi-task generative recommender with three components, each alleviating one collapse. Dual-Stream Decoupling (DSD) injects task identity into computation stream early and separates the shared context stream from the task-specific stream, alleviating signal dilution. Task-Interactive Modeling (TIM) replaces the predefined funnel with explicit cross-task interaction, letting each task condition on the realized outcomes of its predecessors with learned, input-adaptive strength. Hierarchical Querying (HQ) lets each task gather multi-scale information across different layers at different training stages. In offline evaluations, IntHQ consistently outperforms competitive encoder backbones under four representative task-head configurations. Deployed in production on Amap, serving hundreds of millions of users for travel recommendation, IntHQ yields a 1.60% relative UVCTR lift.
Read the full abstract

All authors Junjie Sun, Longfei Xu, Huimin Yan, Wei Luo, Kaikui Liu, Xiangxiang Chu

Information Retrieval

TSPORec: Token Selection via Preference Optimization for LLM-Based Sequential Recommendation

Wenqiao Zhu, Chao Xu, Haipang Wu et al. (+1 more)

Large Language Models (LLMs) have emerged as powerful tools for improving recommendation systems. The effectiveness of LLMs arises from their ability to harness rich textual information and their capacity to model heterogeneous user preferences based on users' interaction history. However, due to the large-scale and deep architectures, LLM-based sequential recommendation approaches generally incur high inference costs, resulting in a low return on investment. To mitigate this cost, many existing approaches resort to using only the first few tokens of item descriptions, which inadvertently discards valuable information contained in the full text, thereby leading to suboptimal recommendation performance. To address this limitation, we propose a novel Token Selection approach for Preference Optimization in LLM-based sequential Recommendation, i.e., TSPORec, which accurately pinpoints informative tokens throughout the entire textual content to improve recommendation performance. Specifically, we design a three-stage pipeline to select informative tokens and introduce a novel proxy reward to facilitate the implementation. TSPORec not only enhances recommendation performance but also improves computational efficiency. Extensive experiments across two models and datasets demonstrate the superb performance (up to 31.25%) and efficiency (up to 63.4%) of our approach compared with six baseline approaches. Code is available at https://github.com/WNQzhu/TSPORec.git.
Read the full abstract

All authors Wenqiao Zhu, Chao Xu, Haipang Wu, Ji Liu

Information Retrieval

MetaStrategy: Generative Ranking with Executable LLM Strategies

Chengyu Lai, Jiuning Lin, Zhibo Xiao et al. (+12 more)

Industrial recommender systems rank heterogeneous content under coupled user, business, commercial, and experience objectives. Existing generative ranking methods typically construct item sequences directly, making them difficult to integrate with mature predictive models, operational rules, and field-level guardrails. We present MetaStrategy, a framework that instead generates a structured, executable ranking strategy. Conditioned on request context, a large language model (LLM) policy emits a typed JSON bundle controlling objective weights, content and category preferences, experience constraints, and position policies. A deterministic validator and compiler instantiate an isolated Generator that competes atomically with incumbents under the list-level Evaluator of the Generator-Evaluator (GE) architecture. We train the policy in a production-path replay environment that re-executes logged requests through the current re-ranking stack without user exposure. The method combines selection, relative-rank, and baseline-lift rewards, a self-competitive curriculum that feeds frequent strategies back as competitors, and Evaluator-routed reward-augmented on-policy distillation that transfers complementary 4B-parameter Teachers into a compact 0.8B-parameter Student. We deploy MetaStrategy in Taobao Homepage Guess You Like through diff-triggered nearline generation; LLM inference remains outside synchronous ranking, with no observable increase in response time (RT). In a seven-day user-randomized online A/B test, MetaStrategy wins 27.93% of treatment-side GE calls and significantly improves click page views (click PV) by 2.11%, item-detail page views (IPV) by 3.12%, and transaction amount by 2.83%.
Read the full abstract

All authors Chengyu Lai, Jiuning Lin, Zhibo Xiao, Xiaodong Zhu, Ruiquan Lan, Bin Zhang, Zihong Huang, Wendong Zhang, Chuxin Chen, Yinjiang Cai, Shuai Zhong, Lingqing Zhang, Dimin Wang, Jialin Zhu, Han Zhu

Information Retrieval

DREAM Technical Report

Bin Zhang, Bowen Zheng, Chao Yi et al. (+74 more)

Industrial recommender systems commonly use cascaded retrieval, ranking, and re-ranking pipelines. Although efficient, these pipelines fragment information and objectives across modules, rely on rigid rules, and have limited awareness of real-time intent, leaving session-level shifts among browsing, comparison, and purchase insufficiently addressed. We present DREAM (Developing Recommender Engine with Agentic Methods), an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them. DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%. Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with safety guardrails. A Reward Dual Loop continuously optimizes both components by combining offline simulation for strategy-space exploration with online feedback for outcome calibration, forming a cycle of generation, execution, evaluation, and experience accumulation. Large-scale A/B tests on Taobao's homepage feed show that re-ranking control alone improves IPV by 2.06%, Core IPV by 2.39%, and GMV by 0.88%. Extending control to fine ranking raises these gains to 2.71%, 3.06%, and 1.31%, respectively, while consistently improving PV by more than 1%. These gains require neither replacement of pipeline models nor compromise of serving stability, supporting agentic meta-control as a viable paradigm for industrial recommendation.
Read the full abstract

All authors Bin Zhang, Bowen Zheng, Chao Yi, Chengyu Lai, Dian Chen, Dimin Wang, Gaoyang Guo, Jialin Zhu, Jian Wu, Jing Yu, Jiuning Lin, Lingqing Zhang, Lingyun Zheng, Mao Zhang, Mingming Pan, Ruiquan Lan, Shuai Zhong, Wen Chen, Wendong Zhang, Xiaodong Zhu, Xuan Chen, Xunke Xi, Yifan Lu, Yiheng Wang, Yue Zeng, Yujie Luo, Yuning Jiang, Zhe Hu, Zhibo Xiao, Zihong Huang, Binbin Cao, Bo Zheng, Danning Wang, Dixuan Wang, Ge Fan, Haixia Wu, Han Zhu, Hao Fang, Haoming Chen, Huiping Chu, Jian Wang, Jianjun Wu, Jiawei Wu, Jiaxin Yu, Jingwen Liu, Jinzhe Shan, Kai Meng, Kai Zhang, Keqin Xu, Kewei Zhu, Lang Tian, Leihui Chen, Li Chen, Licheng Xu, Lide Xiao, Ruitong Zhang, Shiyao Peng, Silu Zhou, Tao Wang, Wei Shi, Wenjun Yang, Xiang Chen, Xiang Gao, Xiao Ren, Xu Liu, Xuwen Wang, Yang Li, Yeqiu Yang, Yi Hu, Yichen Yuan, Yinnan Song, Yipeng Yu, Yuan Liu, Yunqi Gao, Zhiliang Huang, Zhujin Gao, Zongyuan Wu

Information Retrieval · Cross-listed from cs.CL

Temporal Misgrounding in Legal RAG: A Versioned-Corpus Benchmark for French Tax Law

Rose Cymbler, Daniel Guez and Laurent Fabre

We identify and quantify temporal misgrounding: the systematic retrieval and citation of the currently in-force version of a legal article when the applicable version is an earlier or future one. Standard legal RAG treats the corpus as static; we argue legal question answering is a temporally-indexed retrieval problem. We introduce FiscalQA Pro, pairing a versioned corpus of 32,436 article-versions of the French tax code (93 years, 1938-2031) with an all-model-hard temporal-reasoning track: 209 scored, expert-reviewed questions across 33 CGI articles (221 released; twelve flagged out of the answerable scope). At selection time, no evaluated model recovered its date-applicable answer closed-book in any of four sampling draws, and the currently in-force text lacks the gold value for all but one of the scored questions. Answers are scored deterministically via atomic ground-truth "nuggets" (regex and numeric-with-tolerance), never LLM-as-judge: an LLM judge would inherit the temporal bias it is meant to score. Across eleven models (five frontier closed-API systems plus Gemini 2.5 Pro as a substitute entry, and five open-weight), parametric knowledge yields 3.0% mean strict accuracy and RAG over a static current-version corpus 2.7%. Static RAG retrieves the date-applicable version 0% of the time, confidently citing a real but inapplicable version. Our end-to-end retriever over a multi-version index, with no oracle, reaches 98.3% mean strict; an oracle-article ablation reaches 99.1%, locating the residual gap in first-stage recall, not version selection. We additionally release a version-aware jurisprudence dataset of 69,208 citation links, together with the corpus, benchmark, model responses, and pipeline code.
Read the full abstract

Information Retrieval · Cross-listed from cs.CV

GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views

Jiahui Cui, Yan Zhao, Kan Wei et al. (+4 more)

Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation. However, the inherent wide field of view and overhead perspective of drone scenarios impose dual challenges on vision-language understanding. At the macro level, overwhelming background clutter in visual representations leads to Cross-Modal Focus Misalignment, where the model prioritizes global environmental similarities over specific object details. At the micro level, Visual Isomorphism creates ambiguity, where candidates share similar geometric structures yet differ only in subtle attributes. To address these challenges, we propose the Granularity-Aware Region Alignment and Semantic Prototype (GRASP) learning framework, enhancing discriminative capability through two synergistic strategies. Specifically, we introduce Region-Focused Alignment (RFA) to promote object-centric cross-modal alignment while suppressing background interference. Concurrently, to tackle visual isomorphism, we propose Semantic Perturbation Enhanced Matching (SPEM), which leverages a foreground-purified Semantic Prototype Codebook (SPC) to construct semantically perturbed negatives for fine-grained semantic discrimination. Extensive experiments on the GeoText-1652 benchmark and the unseen ERA dataset demonstrate that GRASP achieves competitive performance in drone-view fine-grained image-text retrieval, validating its effectiveness for cross-modal understanding in aerial scenarios. Our code implementation is available at https://github.com/UCAS-JC/GRASP.
Read the full abstract

All authors Jiahui Cui, Yan Zhao, Kan Wei, Enze Zhu, Peirong Zhang, Lei Wang, Yiru Wang

Information Retrieval

RVANNS: Mixed-Precision Indexing and Locality-Aware Graph Traversal on RISC-V

Chengying Huan, Yudong Liu, Jianguo Wang et al. (+9 more)

Approximate nearest neighbor search (ANNS) on CPUs is increasingly constrained by candidate-vector movement and decoding rather than peak arithmetic throughput. Although the RISC-V Vector Extension (RVV) provides vector-length-agnostic execution and LMUL-based register grouping, generic low-precision decoding still incurs conversion overhead, while irregular graph traversal generates scattered accesses that degrade cache locality and memory-level parallelism. We present RVANNS, an RVV-oriented ANNS engine that jointly optimizes vector representation and graph locality. Its Mixed-Precision Multi-Layer Index (MPMI) represents each vector with a dense 8-bit affine base and sparse FP16/FP32 residuals, fusing reconstruction with distance accumulation and aligning widening with LMUL-sized register groups. ROrder co-locates likely co-visited graph nodes and sorts remapped adjacency lists, transforming scattered payload probes into denser, predominantly forward-moving address streams. Integrated into Milvus, RVANNS achieves 3.39x and 4.94x speedups over scalar execution on real 128-bit and 256-bit RVV processors, respectively. Under controlled HNSW configurations, it improves throughput by 2.27–2.76x over RVV SIMD+FP32 and by 1.18–1.59x over the corresponding AVX-512 and SVE baselines. On Cohere10M, it further delivers 1.82–2.27x higher QPS/W than the evaluated GPU baselines.
Read the full abstract

All authors Chengying Huan, Yudong Liu, Jianguo Wang, Lizheng Chen, Renling Yin, Weijia Chen, Ji Qi, Jiageng Yu, Junjie Xu, Jie Zhang, Chen Tian, Yanjun Wu

Information Retrieval

PreGress: Ranking-Native Pre-training and Prompting for Graph Node Ranking

Lujie Ban, Jiasheng shi, Yingli Zhou et al. (+5 more)

Node ranking is a fundamental problem in graph information retrieval, measuring the relative importance of nodes and supporting a wide range of applications such as influence analysis, recommendation, and graph-based retrieval augmented generation. However, exact computation of graph-based ranking measures is often computationally prohibitive at scale. Existing GNN-based ranking methods provide scalable approximations, but they are typically tailored to individual ranking criteria and require retraining for each downstream task, which limits their transferability and efficiency. Recent graph pre-training approaches aim to enable knowledge transfer across tasks, yet their learning objectives are largely misaligned with node ranking, resulting in suboptimal adaptability to ranking-oriented applications. To address these limitations, we propose PreGress, the first ranking-native pre-training and prompting framework for supporting a wide range of node ranking tasks. PreGress performs multi-task pre-training using our carefully designed objectives, including degree centrality prediction and attribute reconstruction, to jointly capture structural and attribute information. To support heterogeneous ranking criteria, we design lightweight, task-specific prompt modules that adapt a frozen ranking backbone to downstream tasks without full retraining. Experiments on six public graphs and two real-world query-to-item benchmarks—Yelp2018 and MovieLens-100K—together with a controlled five-criterion graph-access study demonstrate strong ranking quality with low task-specific state overhead.
Read the full abstract

All authors Lujie Ban, Jiasheng shi, Yingli Zhou, Kaiwen Xue, Daiyin Wang, Xubin Li, Shuanghua Li, Chenhao Ma

Information Retrieval

Guardian Crawler: Retrieval-First Knowledge Discovery with Bounded LLM Augmentation for Noisy Web Intelligence

Joshua Castillo, Santosh Nukavarapu and Ravi Mukkamala

Retrieving relevant evidence from noisy web data is challenging, particularly in sensitive domains containing incomplete reports, heterogeneous language, and irrelevant content. We present Guardian Crawler, a reproducible retrieval-first testbed for controlled experiments on knowledge discovery and evidence-grounded summarization over synthetic web-like corpora. The architecture combines BM25 retrieval with risk-aware, embedding-augmented, and hybrid reranking, followed by constrained retrieval-augmented generation with explicit document citations. Experiments on a synthetic 900-document corpus and 10 queries produced the highest descriptive retrieval scores under risk-based reranking, with P@10 = 1.00 and NDCG@10 = 0.94, compared with 0.94 and 0.81 for BM25. The best hybrid and BM25+Semantic configurations reached NDCG@10 values of 0.94 and 0.88, respectively. All 41 evaluable generated bullets passed the lexical coverage threshold; an automated LLM judge classified 36 as supported, one as partially supported, and four as unsupported. These results demonstrate the feasibility of Guardian Crawler as a controlled testbed but do not establish statistical superiority, human-validated faithfulness, or transfer to live-web investigative environments.
Read the full abstract

Sunday 9 August

Information Retrieval

What Would Fix This RAG Failure? Auditing Counterfactual Response with Paired Evidence Interventions

Wenzhang Du

A failed retrieval-augmented generation (RAG) answer can be consistent with several unseen responses to evidence repair. We introduce Pair-ID, an offline audit that holds one query, retrieval state, and reader constant, then crosses two operations, adding missing support and deleting verified nonsupport, to measure a same-failure counterfactual response vector. A complete funnel over 19,981 benchmark queries identifies 11,105 eligible Qwen failures, from which a prospectively fixed SHA-256 ordering selects 1,200 before generating any sampled response. Among 1,190 regenerated-valid failures, support addition repairs 197/600 JOINT cases (0.328, 95% CI [0.292, 0.367]), and deletion repairs 162/1,190 cases (0.136, 95% CI [0.117, 0.155]); length- and position-matched shams retain semantic contrasts of 0.223 and 0.101. The original view carries partial predictive signal for individual response cells (macro AUROC 0.678; Brier 0.152 versus 0.160 for a marginal baseline), but exact-vector accuracy, 0.637, does not exceed the 0.646 majority-vector baseline, and vector macro-F1 is 0.170. Across four readers, both marginal sensitivities recur, while pooled exact-vector agreement is 0.675-0.765 and JOINT-only agreement falls to 0.538-0.691. These results show that evidence sensitivity occurs at meaningful rates in the hash-selected eligible-failure sample, is only partially predictable from the observed failure, and is conditional on the reader. The evidence supports a frame-scoped offline response audit, not an information-theoretic impossibility result, reader-independent taxonomy, or runtime repair policy.
Read the full abstract

Information Retrieval

Difficulty-Gated Fusion of Reasoning Views for Temporal Retrieval

Jamie Holdcroft, Abdelrahman Abdallah and Adam Jatowt

Reasoning-intensive temporal retrieval requires matching a query to documents whose relevance depends on shared temporal reasoning rather than lexical overlap. Expanding a query into several reformulations that make its temporal intent explicit, and retrieving with each, supplies this reasoning, but fusing the resulting rankings with equal weights wastes accuracy: for any single query, only some reformulations are reliable. We propose query-difficulty-gated fusion of reasoning views. From each view we read an eight-dimensional signature of its score distribution, built from query-performance-prediction quantities such as softmax entropy, score gaps, and dispersion, and a gate of roughly one thousand parameters maps these signatures to per-query view weights. The fused ranking uses no relevance labels at inference, no re-ranking, and no fine-tuning of the retriever; the gate is trained leave-one-task-out. On the Tempo benchmark, the method improves all six retrievers we evaluate, from BERT encoders to 7B decoder retrievers, with the largest gains on the weaker backbones. The strongest retrievers reach $0.297$ and $0.303$ nDCG@10, and the per-query gain over the original query is significant under a paired bootstrap ($p<0.001$). A per-query oracle reaches $0.364$ against our realized $0.297$, exposing headroom that identifies per-query view selection as a concrete next step.
Read the full abstract

Information Retrieval

A Symmetric Layer-Union Audit of Component Collapse in Hierarchical Procedural Corpora

Jiuyi Zheng and Gan Xu

Component-disjoint leakage control can group corpus units by content similarity, hierarchical membership, or both. Guvenilir and Dogan previously showed that merging relation types can create a giant component that obstructs splitting; we do not claim this phenomenon as new. We examine it through a symmetric audit of a content-near-duplicate layer, a common-container layer, and their union in a fixed panel of six hierarchical procedural corpora. MyFixit and Doc2Dial exhibit the individual-layer-pass/union-fail pattern under the same operational criteria. The resulting two-of-six fraction describes this deliberately constructed panel and is not a prevalence estimate. A prespecified bridge-specific predictor is associated with the pattern, but it is not distinguished from a registered union-density control; the panel therefore does not identify a bridge-specific mechanism. Secondary diagnostics bound the interpretation of threshold sensitivity, annotation coverage, and lexical cues without extending those findings beyond their recorded sources and definitions. The paper's contribution is a bounded measurement and audit: it keeps relation families visible, evaluates their individual and union component structures symmetrically, and reports negative cases and mechanism limits. It proposes neither a new splitting algorithm nor a general causal claim about relation unions.
Read the full abstract

Information Retrieval · Cross-listed from cs.CY

Automating Freshman Course Placement and Registration: A Case Study

Bharathwaj Vijayakumar, Samyukta Alapati and Sahana Varadaraju

This implementation report explores Rowan University's effort to automate the process of freshman course placement and registration. Historically, Freshman Instructional Guides (FIGS) at Rowan was manually executed, requiring significant time from Testing Services, University Advising, and the Registrar's Office to evaluate placement needs and assign students to courses. Given the 57% surge in first-time degree-seeking student enrollment over a decade, the manual processes became increasingly unsustainable. In response, a cross-departmental team developed a comprehensive automated process to integrate data from Banner (Student Information System), Google Sheets maintained by Advising, and other sources. This automated process classifies students based on program groupings, determines primary and secondary course placements, checks for real-time availability and constraints in Banner, and completes course registration for freshmen in bulk. The resulting system processed over 3500 incoming students with over 350 hours in annual time savings, reduced the potential for human error, and enabled staff to shift focus from administrative work to strategic advising. This report outlines the implementation context, design architecture, technical integration, assessment methods, lessons learned, and practical implications for institutions with similar challenges.
Read the full abstract

Information Retrieval

BOUND: Brief-Guided Corrective Preference Distillation at Search-Control Boundaries

Qingying Niu, Ruiyang Ren, Wayne Xin Zhao et al. (+1 more)

Large language model (LLM)-based deep search agents solve tasks through iterative retrieval and reasoning, but locally relevant evidence can cause persistent wrong-anchor drift, constraint drift, or local-topic drift. Existing methods supervise trajectories, outcomes, or steps, but rarely distinguish task-aligned continuations from locally plausible ones that reinforce drift. We propose BOUND, a brief-guided corrective preference distillation framework for persistent search drift. For each student-induced decision-time state, BOUND constructs a teacher-side search-state brief that preserves the original search target and key constraints while summarizing confirmed evidence, missing information, and drift status. Guided by the brief, the teacher determines whether the student's continuation contains a correctable local search-control error likely to affect subsequent decisions. Together with the rollout outcome, this assessment determines whether to construct a corrective contrast between a student-specific correction and the original continuation, or a termination contrast between a supported answer and an unnecessary retrieval continuation. Each validated state-matched preference pair operationalizes a search-control boundary. Direct preference optimization (DPO) distills these preferences into the student, while the brief and teacher-side computation remain confined to training. We evaluate BOUND on four multi-hop QA benchmarks and three deep-search benchmarks. Across the six benchmarks for which we reran baselines, BOUND leads on five datasets and 12 of 14 metrics. Under the same search-control interface and matched settings, BOUND outperforms Trajectory SFT by 5.6 EM points on Bamboogle and 4.8 accuracy points on BrowseComp-Plus. Code is available at https://github.com/RUCAIBox/BOUND.
Read the full abstract

All authors Qingying Niu, Ruiyang Ren, Wayne Xin Zhao, Yaliang Li

Information Retrieval · Cross-listed from cs.CV

AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval

Haoyu Zuo, Yibo Yan, Xin Zou et al. (+4 more)

Multi-vector vision-language retrievers enable fine-grained Visual Document Retrieval (VDR) through late interaction, but storing and scoring hundreds of visual patch embeddings per page incurs substantial overhead. Existing training-free methods rely on pruning or merging: pruning degrades sharply under aggressive compression, whereas merging does not explicitly prioritize important regions when forming representatives. We introduce AnchorFold, a training-free focus-then-fold framework for document-side index compression. AnchorFold applies Recursive Attention Propagation over visual self-attention graphs, performing multi-step propagation within each attention head and integrating scores across heads and layers. The focus stage selects the highest-centrality tokens as anchors. The fold stage assigns remaining tokens to their most similar anchors in the normalized retrieval space and summarizes each anchor-centered group through centrality-weighted aggregation. This preserves non-anchor contributions while concentrating capacity on structurally important tokens. Across ViDoRe v1/v2 and REAL-MM-RAG with three diverse retrieval backbones, AnchorFold consistently outperforms all evaluated training-free baselines at $\gamma \leq 0.20$. On ViDoRe v1/v2, it retains 98.3% of full-index NDCG@5 on average at $5\times$ compression, achieving near-lossless compression, and 92.4% at $20\times$ compression.
Read the full abstract

All authors Haoyu Zuo, Yibo Yan, Xin Zou, Shuliang Liu, Yi Cao, Mingdong Ou, Xuming Hu

Information Retrieval · Cross-listed from cs.CR

HaloMark: A Spectral Threshold for Embedding-Vector Watermarking under C2PA

Tarun Sharma

Foundation-model embeddings are now a primary data asset, but the content-provenance machinery built for images and audio does not transfer to them. C2PA binds to an asset with a stable bit-level or perceptual identity; embeddings have neither, since quantisation, projection, fine-tuning, and windowed averaging reshape them in normal use and break any fixed hash. We present HaloMark, a watermark for embedding vectors cryptographically bound to a C2PA manifest. It composes four standard primitives – a block-diagonal orthogonal rotation, public whitening, an input-dependent LSH commitment, and a per-vector nonce – around one protocol change: the producer signs the LSH commitment c into the C2PA sidecar, and the verifier reads c from the manifest instead of recomputing it. Recomputing is fragile under whitening, which flips the commitment bucket on 62% of inputs at cos = 0.96; reading the signed c reduces the verifier's score to T = T_null + beta(A)*epsilon, so security turns on a single scalar beta, which we bound rigorously for linear and non-adaptive attackers and characterise empirically for the adaptive case. We evaluate against an adversary holding polynomially many clean/watermarked pairs under one key with full sidecar visibility, across eight baselines and ten adaptive attackers including denoising-autoencoder removal. The eleven encoders separate at an empirical threshold eff_rank(Sigma)/d ~= 0.19: above it, detection AUROC stays at 0.98 or higher across every in-budget attack on the three encoders we sweep in full, and at 0.965 or higher under single-seed DAE removal on the rest; below it every variant we tested fails. Why the threshold is dimension-uniform is left open. Deployed as a Qdrant admission filter, the verifier runs at 284 us and 24 bytes of sidecar per vector, validated end-to-end against three C2PA reference-SDK bindings.
Read the full abstract

Information Retrieval · Cross-listed from cs.CL

Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach

Tong Bao, Yi Zhao, Heng Zhang et al. (+1 more)

Scientific named entity recognition (SciNER) plays a crucial role in information extraction and knowledge discovery from scientific texts. Recently, large language models (LLMs) have demonstrated the capacity to achieve competitive SciNER performance with minimal human effort. Existing research highlights the importance of incorporating candidate entity type information for accurate entity recognition and classification by LLMs. However, when too many candidate entity types are provided in the prompt, LLMs struggle to accurately recognize and label entities in scientific texts, where entity types are more complex than in general domains. To address this challenge, we propose TdSciNER, a type-driven approach that effectively leverages entity type information to enhance SciNER performance. In TdSciNER, we first design an entity type filter model to identify the most likely entity types present in a given sentence. Subsequently, we introduce an auxiliary multi-class entity typing task within a multi-task learning framework alongside SciNER to obtain richer contextual representations. Then, we develop a novel demonstration selection strategy based on sentence similarity and entity type diversity to activate the in-context learning capabilities of LLMs, thereby improving entity recognition accuracy across diverse scientific domains. Experiments on three datasets demonstrate that our method achieves performance comparable to fully supervised models. Further analysis validates that each entity type-driven component in TdSciNER contributes to the improvement of SciNER performance. This work provides valuable insights for future advancements in SciNER and broader information extraction tasks in scientific text mining.
Read the full abstract

All authors Tong Bao, Yi Zhao, Heng Zhang, Chengzhi Zhang

Information Retrieval · Cross-listed from cs.AI

Can Open-Weight Models Compete on Financial Text Comprehension?

Jan Spörer

Open-weight language models from Chinese AI labs caught up on benchmarks relative to proprietary frontier models in recent months. Yet their reliability on real-world financial tasks remains largely untested. We updated the Financial Touchstone benchmark, which now has 2,967 question context-answer triplets across 495 international annual reports. We also apply a new set of models on the benchmark, expanding coverage from eleven to twenty models across ten providers, including recent open-weight models such as GLM 4.7, GLM 5, Kimi K2.6, and DeepSeek V3.2, as well as Alibaba's proprietary flagship Qwen3-Max. Anthropic's Claude Opus 4.6 achieves the highest accuracy (88.4%), while Google's Gemini 2.5 Pro maintains the lowest hallucination rate (0.08%). Notably, the open-weight Kimi K2.6 ranks third in accuracy, and the non-reasoning models GLM 5 and Mistral 3 rank fourth and fifth, challenging the assumption that reasoning architectures or proprietary weights are a prerequisite for strong financial comprehension. Information retrieval remains the primary bottleneck, accounting for 48.9% of all failures. We also document a new finding: geopolitical content filters in Chinese models refuse legitimate financial questions (0.08% of attempts), sometimes without clear reason, and the refusal behavior depends on the access route as much as on the model. The complete dataset and evaluation framework are publicly available.
Read the full abstract

Information Retrieval

Structure-Preserving Projection for Mitigating Modality Bias in LLM-Based Sequential Recommendation

Tzu-Wei Chiu, Song-Duo Ma, Hsin-Yu Lin et al. (+1 more)

Recent LLM-based recommenders integrate textual and collaborative signals by projecting collaborative embeddings into the embedding space of the LLM. However, this projection can introduce modality bias that distorts the underlying collaborative structure and limits the usefulness of projected embeddings. To address this issue, we propose a novel structure-preserving projection approach that maintains the relational geometry of collaborative embeddings through dedicated structure-preserving losses. Comprehensive experiments demonstrate that our approach consistently improves recommendation performance, providing a more reliable path for LLM-based recommendation.
Read the full abstract

All authors Tzu-Wei Chiu, Song-Duo Ma, Hsin-Yu Lin, Pu-Jen Cheng

Information Retrieval · Cross-listed from cs.AI

LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs

Minhan Cho, Soyoung Park, Kihyeon Jeong et al. (+3 more)

The Model Context Protocol (MCP) standardizes how servers expose data and tools to Large Language Models (LLMs). A common server design embeds frequently used reference data, such as identifier lookup tables, directly in the server instructions: the system-prompt text a server hands to the host application. When a query concerns an entry of the embedded table, the model can act on it immediately instead of re-discovering the same information through a search tool. We test whether client LLMs actually consume such instruction-embedded data, reporting a 54,000-trial study across 24 LLMs (9 Claude, 6 Gemini, 9 GPT) on a production legal-information MCP server. A diagnostic condition that removes the competing search tool shows that failures are dominated by behavioral preference rather than missing capability. With search unavailable, 23 of 24 models read the embedded data reliably (hit ratio at least 98%); with a search tool merely present, 9 models drop below 15%. A 2^3 factorial analysis of three instruction-level interventions reveals strong interaction effects: combining all three restores at least 86% for 20 of 24 models, but individual interventions can backfire for specific model families. Per-server prompt engineering is therefore a workaround rather than a fix; we argue that MCP host applications should provide an explicit mechanism that places server instructions ahead of tool selection in the client LLM's deliberation.
Read the full abstract

All authors Minhan Cho, Soyoung Park, Kihyeon Jeong, Byeongkyu Jeon, Daejin Choi, Jinyoung Han

Information Retrieval

Personalized Communication Skills for Agentic Recommender Systems

Zongwei Wang, Min Gao, Guangyu Hu et al. (+2 more)

Agentic recommender systems increasingly employ large language model-based UserAgents to evaluate candidate items through simulated feedback before recommendations are delivered. However, existing UserAgents typically reason in isolation based on limited personal histories, which may lead to perspective narrowing: the agent evaluates candidates from a local and incomplete view, overlooks relevant preference facets, and consequently produces inaccurate judgments. A natural way to alleviate this problem is to introduce other users as advisor agents, whose diverse histories provide complementary evidence that helps the target user reconsider overlooked preference signals. Nevertheless, a generic user-advisor communication process is insufficient, as different user decision states require different forms of external advice. Based on this insight, we propose AgentCom, a personalized communication skill framework for agentic recommender systems. AgentCom organizes reusable communication skills into a shared why–what–how–who skill bank: why identifies the decision deficiency that necessitates communication, what specifies the information task, how determines the advisor interaction protocol, and who retrieves advisors capable of executing that protocol. To make the shared skill bank personalized at use time and adaptive over time, AgentCom introduces two complementary mechanisms: personalized skill routing and failure-driven skill evolution. Personalized skill routing constructs a communication path by sequentially selecting suitable skills for each user and recommendation context. Failure-driven skill evolution learns from unsuccessful communication cases and enriches the shared bank with reusable skills that address previously uncovered communication needs. Experiments show that AgentCom consistently improves recommendation performance across traditional, social, and agentic recommenders.
Read the full abstract

All authors Zongwei Wang, Min Gao, Guangyu Hu, Xinyi Gao, Junliang Yu

Information Retrieval · Cross-listed from cs.AI

Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

Harshitha Kolukuluru, Reshma Ashok, Kirat Arora et al. (+7 more)

Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional evidence often declines. This leads to unnecessary token cost, higher latency, and noisier inputs for final report generation. We study marginal value estimation for context management in deep research agents and present the first systematic stage-aware comparison of pruning strategies across the pipeline. We evaluate lightweight heuristic criteria and a learned value model at pre-retrieval, post-retrieval, and pre-synthesis stages. Our results show that pruning effectiveness depends more on where pruning is applied than on the specific scoring rule: early pruning yields the largest end-to-end savings, while later pruning mainly refines the final synthesis context. Lightweight heuristics reduce token usage by up to 73% with little quality degradation, learned pruning remains competitive on selected trade-offs, and no single method dominates across quality, efficiency, and faithfulness. These findings provide practical guidance for designing efficient long-horizon agentic systems.
Read the full abstract

All authors Harshitha Kolukuluru, Reshma Ashok, Kirat Arora, Evan William Ciccarelli, Nischal Ashok Kumar, Lunyiu Nie, Franck Dernoncourt, Samyadeep Basu, Ryan A. Rossi, Nedim Lipka

Saturday 8 August

Information Retrieval

TailSpec-EASE: Knowledge-Graph-Regularized Linear Recommendation for Web Long-Tail Discovery

Jianru Shen

Recommender systems on Web platforms tend to over-serve popular items and neglect the long tail. Item-side knowledge graphs (KGs), often available as linked data or RDF-style Web resources, can help by connecting sparse items through shared semantic attributes. Many competitive KG-aware recommenders rely on graph neural architectures, whereas strong shallow linear models such as EASE-R typically ignore side information and may become infeasible in their global closed-form version. We introduce TailSpec-EASE, a lightweight recommender that injects a relation-aware spectral KG prior into a local closed-form reconstruction objective. The prior strength adapts to item popularity, giving stronger semantic guidance to long-tail items. Across four public benchmarks and a broad set of classical, linear, graph-CF, KG-aware neural, and score-level KG baselines, TailSpec-EASE attains a favorable trade-off between overall accuracy, long-tail performance, and training cost. It improves NDCG@20 by up to 24% over its counterpart without KG information. All tail-metric improvements over the no-KG counterpart are statistically significant under a paired bootstrap, and overall NDCG improves significantly on three of the four datasets. In a representative Amazon-book timing study, TailSpec-EASE trains in 37 seconds on CPU, compared with 2,584 seconds for a GPU-trained KGAT run and 15,800 seconds for CPU LightGCN, while attaining higher NDCG@20 and Tail Recall@20 on that dataset. It also remains feasible on catalogs where the global closed-form model runs out of memory.
Read the full abstract

Information Retrieval

Marginal Expected Revenue for Jointly Ranking Auction and Fixed-Price Listings in E-Commerce Sponsored Search

Greg Kocher and Sanjana Arun

E-commerce search ranking must balance multiple objectives–relevance, user engagement, and platform revenue–when allocating impression slots to competing listings. Estimating the expected revenue component is well understood for fixed-price items, but becomes challenging when marketplace inventory includes mixed listing formats such as pure auctions and hybrid "Auction with Buy It Now" (ABIN) items, where prices evolve dynamically and the final transaction value is unknown at ranking time. Yet auction and ABIN listings account for a meaningful share of inventory and transaction volume on platforms such as eBay, and are a popular format for individual sellers and for unique items with unclear value. We extend the standard Expected Cost-per-Mille (eCPM) framework to auction and ABIN listings by deriving a marginal eCPM (meCPM) that captures the incremental value of showing one more impression of an item whose price is still evolving. The resulting formulation extends the familiar fixed-price eCPM–which is already inherently marginal–to auction dynamics, allowing unified ranking of fixed-price, auction, and ABIN listings under a single objective. We then describe a practical production implementation that approximates this objective, addressing cold-start challenges by bootstrapping from existing engagement models. Online A/B tests at a large e-commerce platform showed positive revenue gains and statistically significant improvements to user metrics, and the system was deployed to production.
Read the full abstract

Information Retrieval · Cross-listed from cs.AI

SuperLocalMemory 4.0: The Governed Memory Operating System for AI Agents

Varun Pratap Bhardwaj, Garima Singh and Arun Pratap Bhardwaj

We present SuperLocalMemory 4.0, a governed, local-first memory operating system for AI agents, unifying multi-channel retrieval under reciprocal-rank fusion, bi-temporal recall, multi-scope isolation, role-based access, verified erasure, and a hash-chained audit trail. A reliability spine governs the primary write path: generation-fenced admission, verifiable memory transactions with per-projection apply, verify, compensate and erase owners, and hash-checkable completion manifests. Eleven fault-injection scenarios, each repeated 200 times, upheld 2,199 of 2,200 scoped component properties. This version leads with a negative result. Ten mechanisms here were implemented, reachable on a live call path, and ineffective at their final connection. Implemented, reachable and effective are three different questions, and the third requires an oracle independent of the mechanism under test. We contribute two mechanical invariants that supply one: a prior-distance assertion over Bayesian learners, and a join-liveness assertion over schema-guarded paths that reports where a guard's missing data resides. A three-arm ablation varying only the recall session-identifier namespace moves no posterior with the defect present and every instantiated arm with it absent, while a negative control that writes every ticket but supplies no engagement settles nothing. We withdraw the previous version's governed write-envelope overhead figure: the two paths it differenced are not comparable. Timing the envelope in place gives an 11.0 ms governed write of which the envelope is 70.6 percent, but the generation fence costs 1.9 microseconds and the obligation ledger 42 microseconds. The cost is durability, not governance.
Read the full abstract

Information Retrieval · Cross-listed from cs.LG

SAGE: SLO-Aware Adaptive Retrieval for Production RAG Systems

Muhammad Faizan Raza, Shuo Yang and Satish Mahadevan Srinivasan

Retrieval-Augmented Generation (RAG) systems in production operate under strict service level objectives (SLOs) on tail latency and infrastructure cost. However, standard retrieval pipelines rely on fixed retrieval budgets that ignore query difficulty, over-retrieving for easy queries and under-serving hard ones, forcing operators to trade answer quality against SLO compliance. This paper proposes SAGE, a learned SLO-aware adaptive retrieval policy that dynamically selects the number of passages k per query. SAGE uses lightweight features derived from initial retrieval (e.g., score distributions, rank gaps, lexical signals) and is trained offline via imitation learning from an oracle that approximates optimal latency-quality trade-offs. At inference, it adds no LLM calls and minimal overhead. On Natural Questions, under a 5s P95 latency SLO, SAGE achieves 95% SLO compliance versus 30% for the best static baseline (k=20), reduces P95 latency by 36% and retrieval cost by 51% with only 2 percentage points Exact Match (EM) loss. A single policy trained on Natural Questions generalizes across HotpotQA, UnSeenTimeQA, and four LLM families (Llama, Qwen, Mistral, Gemma), consistently yielding +45-52 point SLO improvements without quality degradation.
Read the full abstract

Information Retrieval

DS@GT ARC at Touché: Large Language Models for Retrieval-Augmented Debate

Anthony Miyaguchi and Conor Johnston

We extend the DS@GT ARC working-note submission to the Touché 2025 Retrieval-Augmented Debate task. The task has two subtasks: generating the next utterance in a simulated debate, and evaluating debate responses according to the Gricean maxims of Quantity, Quality, Relation, and Manner. The DS@GT ARC submission consisted of six leading LLMs from three providers through a retrieval-augmented prompting pipeline. We summarize the results from the working paper and explore whether multi-LLM evaluator agreement is a reliable proxy for official evaluation performance. The analysis shows that frontier LLM systems are strong response generators, and as evaluators they agree strongly within model families. However this consensus does not reliably track the official evaluation target, with the largest gap on the Quality maxim. The accompanying source code for this paper is located at https://github.com/dsgt-arc/touche-2025-rad and https://github.com/dsgt-arc/touche-2025-rad-analysis.
Read the full abstract