Peer Revenue Publish or profit

Papers

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

Computer Science Information Retrieval

cs.IR Watch Information Retrieval

Wednesday 16 September

Information Retrieval · Cross-listed from cs.AI

Time-Aligned Evolving Concept Graphs for Scientific Relation Forecasting

Fred Sun, Jingze Wang, Minkun Xu et al. (+1 more)

Forecasting scientific relations can guide discovery by identifying promising connections before they emerge. Existing approaches often model concept semantics and graph structure separately or summarize semantics over coarse historical snapshots, leaving semantic representations potentially misaligned with rapidly evolving graph evidence. We propose a time-aligned evolving concept graph framework that jointly models semantic and structural evolution. Its core idea is to treat dated papers as shared update events, reconstructing semantic and structural states from the same publication history through each prediction time. Pair-level fusion combines these states to forecast first co-occurrence, relation formation, and conditional relation type. Holding architecture and training fixed, refreshing context alongside graph updates improves mean relation AUPRC by 16.6% over frozen context. On a graph built from 187,848 papers with 270,687 concepts and 7.45 million co-occurrence links, the complete framework improves mean relation AUROC from 0.9290 for the strongest evaluated baseline to 0.9722, with mean population-weighted AUPRC 0.005778.
Read the full abstract

All authors Fred Sun, Jingze Wang, Minkun Xu, Shangqi Guo

Information Retrieval

PageRecall: Measuring Page Selection in Literature-Grounded Question Answering

Aaditya Chauhan

We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite the page and the table or figure where the answer lives, and answer in a requested format. Our main finding is that evidence grounding is limited by retrieval, not by reading. The page selector put the annotator's page, which we call the gold page, in front of the model that locates evidence only about half the time (52.6% gold-page recall), while that model, given the page, cited the right one in 45 of the 48 locators it emitted (94%). When the page was missing it rarely said so: of 45 such cases it returned nothing 14 times, a wrong page 24 times, and a correct page 7 times, so the pipeline failed quietly almost twice as often as it failed visibly. Since the failure was that the right page was never shown, the fix is to stop choosing: each retrieved paper fits in the model's context, so we show it whole. Page ranking survives only as a fallback inside papers too long to fit, which no test-split paper was, and gold-page recall reaches 100% on the papers we can parse. Separately, questions that identify their target by position rather than content, such as "the first author of the 24th reference", are served by parsing rather than retrieval: we resolve the bibliography into an addressable list, which also supplies identifiers the evidence metric scores. The final system scores 0.762 paper $F_1$, 0.441 evidence $F_1$ and 0.920 multiple-choice accuracy on the held-out test split. Because the pipeline depends on a closed model without seed control, we release a harness that verifies the paper's central claims against committed artifacts.
Read the full abstract

Information Retrieval · Cross-listed from cs.LG

LIGE-GR: A Smooth Leap from Ranking to Generative Recommendation in the LLM Era

Venkat Srinivas, Chenzhang He, Sam Woodmansee et al. (+63 more)

The remarkable success of large language models (LLMs) has provided important inspiration for the next generation of recommender systems. Structurally, recommendation and language generation share a similarity: both aim to produce an ordered sequence that optimizes the user's experience. However, how to precisely absorb the essence of the LLM paradigm into mature industrial recommender systems remains an open problem. There are two challenges. First, it is unclear how to incorporate the LLM paradigm – sequence-level generation and optimization – into recommendation. Second, real-world recommender systems are mature systems that have been iteratively customized for years around specific products, business constraints, serving infrastructure, and organizational ownership. Replacing such systems wholesale is often technically risky and organizationally disruptive. In this paper, we propose LIGE-GR, a listwise generation and evaluation recommendation framework that upgrades from a traditional ranking system (itemwise recommendation) toward a generative recommendation paradigm. Instead of rebuilding the entire recommendation stack from scratch, LIGE-GR generalizes the existing pointwise recommendation system into a listwise generation system. This allows mature recommender systems to benefit from listwise optimization while preserving compatibility with existing models, value functions, and serving infrastructure. We validate LIGE-GR in short-video recommendation on Instagram Reels and Facebook Video. On these recommendation surfaces, LIGE-GR improves time spent by 1.14 percent on Instagram Reels and 0.72 percent on Facebook Video, while requiring only modest additional inference resources.
Read the full abstract

All authors Venkat Srinivas, Chenzhang He, Sam Woodmansee, Shawn Lian, Wenjie Hu, Renjie Jiang, Ziheng Huang, Xinyuan Zhang, Zhihao Zheng, Zhuoran Yu, Rui Li, Lei Yuan, Ziwei Li, Jimmy Jia, Mert Terzihan, Ekrem Kocaguneli, Yiming Liao, Zhichen Zhao, Yue Yin, Yue Weng, Wanli Ma, Xufeng Cai, Weimiao Wu, Yezhou Huang, Du Zhang, Yukun Ding, Aaron Johnston, Yueming Wang, Zhaojie Gong, Yuting Zhang, Serena Li, Adithya Ganesh, Boying Liu, Haichuan Yang, Xialu Li, Matt Ma, Qunshu Zhang, Andrew Ton, Nathan Berrebbi, Neel Pawar, John Joshua Miller, Jayant Subramanian, Praveen Rathinavelu, Cheng Huang, Aadhar Sachdeva, Josh Karns, Andres Aaron Gutierrez, Neil Agarwal, Gustas Pladis, Vladimir Batygin, Gopal Ray, Aditya Priyadarshi, Shantanu Patil, Zhe Wang, Penny Pan, Yiping Han, Arun Singh, Guangdeng Liao, Bi Xue, Xinyao Hu, Yang Song, Yisong Song, Meihong Wang, Haotian Wu, Deepak Agarwal, Ji Liu

Information Retrieval

DUPAR: Dual-Path Conversational Retrieval via Speech Retriever with Cross-Turn Evidence Caching

Yuanjun Li, Yiwen Liu, Dapeng Li et al. (+4 more)

Voice assistants grounded in external knowledge typically use automatic speech recognition (ASR) to transcribe speech queries before retrieving evidence from textual knowledge bases. This cascade adds latency and propagates recognition errors, whereas direct speech retrieval is vulnerable to cross-modal misalignment. To address these limitations, we propose DUPAR, a conversational retrieval framework with complementary slow and fast paths. The fast path uses a task-adapted audio encoder aligned with frozen BGE-M3 text embeddings to search a cross-turn evidence cache. When cache confidence is insufficient, the slow path fuses full-index retrieval using audio and ASR-transcript embeddings, and the selected evidence refreshes the next-turn evidence cache through one-hop graph expansion. On a domain-specific knowledge base, our trained audio encoder approaches text-retrieval accuracy on clean speech with a 3.75$\times$ query-side speedup over ASR + Text Encoder. It raises average Recall@10 from 0.771 to 0.875 on the noise benchmark and improves overall Recall@1 by 4.2 percentage points across synthesized speaking styles. Compared with full-index audio retrieval, cross-turn evidence caching significantly reduces retrieval errors when the previous turn retrieves correct evidence and the follow-up targets a one-hop neighboring chunk.
Read the full abstract

All authors Yuanjun Li, Yiwen Liu, Dapeng Li, Zhiwei Xu, Bin Zhang, Shengtao Zhang, Rong Shen

Tuesday 15 September

Information Retrieval · Cross-listed from cs.CL

Parser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents

Shubham Kumar Singh

Retrieval-augmented generation (RAG) pipelines are typically assembled from independently-chosen components – a document parser, a chunking strategy, and an embedding model – yet these choices are rarely evaluated jointly, and evaluations that do combine them are usually run on a single document or corpus. We present a controlled factorial study of 3 parsers, 3 chunking strategies, and 5 dense embedding models, together with a sparse BM25 baseline, evaluated against 800 question instances, each with one or more required evidence strings, with evidence strings automatically validated against source text and a 10% random sample manually reviewed, across four structurally distinct Indian central-government regulatory documents. We fit linear mixed-effects models with document-query-level random intercepts to the resulting 72,000-row result set, run Holm-corrected paired comparisons between matched dense and sparse configurations, and report clustered bootstrap confidence intervals for all 54 unique retriever configurations. We find that no single retriever family dominates across documents; parser and chunker choice interact significantly; MPNet-base is a consistent underperformer with a severe failure mode on table-derived questions; and the corpus exhibits a near-saturated evidence-preservation ceiling above 98%, indicating that retrieval differences are driven primarily by ranking quality rather than information loss during ingestion. We additionally report embedding-dimension and chunk-size/overlap ablations and an efficiency/quality Pareto analysis. We release our full evaluation harness, corpus manifest, and 800-question benchmark.
Read the full abstract

Information Retrieval · Cross-listed from cs.LG

From Phase Transition to Systemic Failure: A Decoupled Analytics Framework for GNN Robustness

Shuai Yan, Dan Peng, Jie Li et al. (+1 more)

Data quality is a major bottleneck for the reliable deployment of graph neural networks (GNNs) in real-world graph mining tasks. Among various sources of degradation, label noise and feature distribution shift (hereafter referred to as distribution shift) are two common yet fundamentally different challenges. To study their effects under controlled conditions, this paper constructs a synthetic homophilic graph regression benchmark in which the two factors can be manipulated separately. A total of 41 configurations and 410 runs are conducted to evaluate the behavior of representative GNN models under varying noise and shift conditions. The results show two distinct patterns. First, under additive label corruption, performance remains relatively stable over a broad range of noise settings and begins to deteriorate sharply only after an observed transition region around the 50 percent noise ratio. Second, under extreme feature distribution shift, all tested models suffer substantial degradation, with test MSE increasing by 48 times to 316 times and correlation dropping by 73 percent to 89 percent. These findings suggest that, in the present controlled setting, GNNs are considerably more tolerant to moderate label perturbation than to severe distribution mismatch. The study provides a controlled empirical baseline for understanding how data quality affects GNN-based graph mining systems and offers practical implications for deployment-oriented monitoring and model maintenance.
Read the full abstract

All authors Shuai Yan, Dan Peng, Jie Li, Ke Wang

Information Retrieval · Cross-listed from cs.CL

How Calibration Content Shapes Attention-Based Reranking

Petros Karypis, Hossein Rajaby Faghihi, Peter Chen et al. (+4 more)

Attention-based rerankers score documents by aggregating query-to-document attention and subtracting a null-query calibration pass to remove positional and structural bias. Although widely used, this calibration assumes that the null pass removes irrelevant signal from each document. We show that modern prompt content, e.g. constraints, instructions, personas, and demonstrations can violate this assumption when it enters the scoring readout, making the null pass relevance-aware rather than null. We find that calibration is especially harmful when applied to prompts containing longer, more detailed instructions as the null-pass step removes relevant signal. Based on these findings, we propose interpolated null calibration, a training-free modification that controls how much of the instruction content enters the null baseline. It recovers attention-based reranking performance on instruction-heavy tasks where standard calibration fails, while preserving calibration's benefits when the null pass remains relevance-agnostic. On instruction heavy tasks, the recovered rankings surpass generative rerankers. We also show that in-context demonstrations improve attention-based reranking with little calibration interference, since demonstrations act only through the query pass and leave the null pass unchanged.
Read the full abstract

All authors Petros Karypis, Hossein Rajaby Faghihi, Peter Chen, Rui Zhu, Noveen Sachdeva, Yan Zhu, Julian McAuley

Information Retrieval

One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG

Neeraj Anand, Payel Santra, Partha Basuchowdhuri et al. (+2 more)

Retrieval-Augmented Generation (RAG) systems typically employ fixed retriever and generator configurations across queries, despite substantial differences in query complexity and information needs, leading to inefficient allocation of computational resources. While retrieval and generation adaptivity have been studied independently, their joint effect on end-to-end RAG performance remains underexplored. We systematically analyze how retriever and generator complexity interacts across factoid and multi-hop question answering (QA), including bridge and composition reasoning tasks. Our analysis shows that stronger retrieval generally yields larger gains than increased generation effort, but both exhibit diminishing and non-monotonic returns, indicating that higher-complexity configurations are not uniformly better across queries. Motivated by these findings, we introduce DRAG, a query-adaptive framework for selecting retriever-generator configurations. We first propose DRAG$_\text{QPP}$, a training-free routing approach that uses Query Performance Prediction (QPP) signals to guide retriever selection and perplexity-based measures over retrieved context to guide generator selection. We further introduce DRAG$_\text{SFT}$, a supervised routing approach that fine-tunes an LLM to jointly predict retriever-generator configurations. Across three LLM families and four QA benchmarks, \qpprag~achieves performance comparable to strong static RAG baselines while substantially reducing inference latency, whereas DRAG$_\text{SFT}$ consistently improves effectiveness over static and training-free adaptive baselines. Overall, DRAG demonstrates that jointly adapting retrieval and generation achieves a more favorable effectiveness-efficiency trade-off than static RAG pipelines.
Read the full abstract

All authors Neeraj Anand, Payel Santra, Partha Basuchowdhuri, Debasis Ganguly, Sumit Bhatia

Information Retrieval

Scaling Articulated Rationales for MLLM-based Recommendation

Haoke Xiao, Yueyang Liu, Yuhui Zhang et al. (+17 more)

We presented SARA, an industrial framework that transforms sparse articulated user rationales into scalable recommendation signals. Its data engine curates questionnaire responses into SARA-HQ, providing explicit preference supervision for aligning SARA-7B through SFT and Quality-Refining DPO. This alignment extends rationale generation from $86{,}564$ questionnaire-covered authors to the full $10$M-author space. SARA-Ranker translates the generated positive and negative rationales into features for user–author interaction modeling and negative-feedback history modeling, connecting articulated reasons to production ranking. Evaluation on unseen authors demonstrates that SARA-7B generates more specific, relevant, and grounded rationales than the evaluated general-purpose MLLMs. On top of a strong industrial ranking baseline with multimodal features, separate online A/B tests show that positive-rationale integration increases watch time by $0.99\%$, while negative-rationale integration reduces Hate feedback by $8.16\%$. Daily refresh and more than $30$ days of production deployment further demonstrate the operational feasibility of the approach. These findings establish articulated rationales as a useful complement to behavioral and content signals, and demonstrate a practical role for MLLMs in scaling sparse human explanations into preference information that improves industrial recommendation.
Read the full abstract

All authors Haoke Xiao, Yueyang Liu, Yuhui Zhang, Xiang Chen, Yufei Liu, Jia Xu, Yalong Guan, Xiaolan Zhu, Xiaoyu Zhang, Shijun Wang, Shuang Yang, Zijie Meng, Zejian Zhang, Ruochen Yang, Xiangyu Wu, Tingting Gao, Han Li, Lantao Hu, Cheng Luo, Kun Gai

Information Retrieval · Cross-listed from cs.HC

Lexplorer: Navigating the Complexity of Legal Document Landscapes

Daniel Fürst, Titus Pünder, Maximilian T. Fischer et al. (+1 more)

As technological and social innovations create novel regulatory challenges, legal systems grow in complexity - increasing the need for interfaces that enable effective interactions with legal document collections. Through interviews with legal scholars (n=15), we find that supporting legal work requires going beyond retrieval-centered legal-information-system paradigms. Hence, we propose Lexplorer, a flexible interface for exploring, navigating, and analyzing legal documents, based on a taxonomy capturing user intents. Distinguishing text and data views for one, few, and many documents, Lexplorer enables context-sensitive interactions with evolving collections of interconnected legal texts, facilitating Adaptive Meaning Construction in law. We evaluate Lexplorer with legal scholars (n=20) in the context of European Union law, validating our elicited requirements, intent taxonomy, and prototype design. Resulting from a close collaboration between visual-analytics researchers and legal scholars, our work also provides nuanced insights into the process required to design interactive systems for expert domains driven by implicit methodological knowledge.
Read the full abstract

All authors Daniel Fürst, Titus Pünder, Maximilian T. Fischer, Corinna Coupette

Information Retrieval · Cross-listed from cs.CL

Diagnosing the Fact-Grounding Gap in Multi-Hop Question Answering

Kevin Mo, Nathan Mo and Richard Zhu

Multi-hop question answering requires combining information from multiple documents to answer complex questions. These systems have grown increasingly capable, yet when they fail, the error is typically attributed to not finding the right documents. Whether this holds at the level of individual reasoning steps remains largely unexamined. We investigate this across three standard multi-hop QA benchmarks and find that failures decompose into two distinct modes: retrieval failures, where the needed passage was not retrieved, and extraction failures, where the passage was retrieved but the needed fact could not be extracted - a phenomenon we term the fact-grounding gap. Extraction failures account for nearly half of all per-hop deficiencies and are invisible to standard retrieval metrics. They remain unresolved by every retrieval intervention we test, establishing a ceiling for retrieval-only improvements. The gap's severity varies across benchmarks and question types, but extraction failures appear on every dataset we measure. Our findings reveal that retrieval failures and extraction failures are fundamentally different bottlenecks requiring different solutions - a distinction absent from current evaluation practice.
Read the full abstract

Information Retrieval

Efficient Swing Computation for Retrieval in Large-Scale Recommender Systems

Runhao Jiang and Renchi Yang

Given a user-item graph $G$, a query item $v_q$ and a target item $v_t$, the Swing score $sw(v_q, v_t)$ of the item pair $(v_q, v_t)$ leverages the user-item-user interaction structure to evaluate their similarity. This measure is found to be highly effective in item-to-item (i2i) retrieval task and finds extensive applications in industrial-scale recommender systems. However, existing solutions towards computing Swing scores are either prohibitively expensive due to their quadratic time complexity w.r.t. the item degree, or rely on truncation heuristics that yield unsatisfactory quality, rendering them impractical particularly on graphs with billions of interactions. In this paper, we present ASC and $K$-ASC, two novel and efficient algorithms for approximate and top-$K$ Swing queries, to address the aforementioned limitations. Specifically, these algorithms provide rigorous theoretical guarantees in probabilistic relative and additive errors of Swing values. The basic idea of ASC is to combine two randomized algorithms, GNS and USS, in a simple yet non-trivial way to adaptively process high- and low-degree query items with minimal runtime cost. In particular, $K$-ASC offers practical efficiency and effectiveness for top-$K$ queries through a filter-refinement paradigm with carefully-designed heuristics. Extensive experiments over eight real datasets demonstrate that ASC and $K$-ASC can achieve orders of magnitude speed-up over competitors in terms of computational time while offering the same approximate and top-$K$ query result quality, and in particular, $K$-ASC is highly efficient on massive graphs including the billion-edge Yambda and MAG datasets.
Read the full abstract

Information Retrieval · Cross-listed from cs.CV

RegRet: Enhancing Region-Level Retrieval in Large Multimodal Models

Xun Liang, Honghui Yang, Weihang Pan et al. (+6 more)

Region-level retrieval aims to align user-specified image regions with relevant regions or textual descriptions, playing a crucial role in realworld applications such as e-commerce product search and RAG. Although recent Large Multimodal Models (LMMs) have made significant strides in multimodal retrieval, they primarily focus on global-level tasks and struggle to capture effective region-level representations. To bridge this gap, we present RegRet, an LMM-based Region-level Retrieval framework that enhances the regional representations without compromising overall global retrieval performance. At its core, RegRet integrates a Region-Aware Encoder to capture detailed regional features while balancing them with the global background context. To further enhance the fine-grained understanding and discriminability of representations, we design a multi-stage training pipeline that includes detailed localized captioning and regional contrastive learning tasks. In addition, considering the absence of region-level contrastive training data and the limited diversity of evaluation tasks in current benchmarks, we introduce the REGMB benchmark. It comprises 225k contrastive pairs, covering four multimodal retrieval tasks. Extensive experiments validate the effectiveness of our approach. RegRet outperforms strong baselines in the zero-shot setting. Further training with contrastive learning leads to an average improvement of more than 20% on both REGMB and public benchmarks, while achieving comparable or better results on global-level retrieval tasks.
Read the full abstract

All authors Xun Liang, Honghui Yang, Weihang Pan, Ruisi Zhao, Boyuan Pan, Yao Hu, Wenxiao Wang, Binbin Lin, Deng Cai

Information Retrieval · Cross-listed from cs.AI

Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?

Younes Boufouss, Luc Pommeret, Thomas Gerald et al. (+2 more)

While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This paper explores whether NLI can be performed using only interpretable, graph-based representations of evidence. We introduce a fully graph-based pipeline where the classifier never directly processes the input text. Instead, sentences are decomposed into atomic propositions, converted into ConceptNet triples via constrained decoding, and represented as three graphs per pair: premise, hypothesis, and a retrieved ConceptNet subgraph. These graphs are then fed into a fine-tuned 0.8-billion-parameter language model. On the SNLI dataset, our pipeline achieves 89.7% accuracy, just 1.9 points below an identically trained text-based model. On ANLI, it matches the published performance of RoBERTa-large on rounds R2 and R3 (48.0% vs. 48.9% and 44.9% vs. 44.4%) but trails by 16 points on R1, resulting in an overall gap of 9 to 14 points compared to its text counterpart. We term this gap the price of interpretability and demonstrate that it stems from representational limitations rather than data constraints. Ablation studies further reveal that graphs and text are complementary: combining both modalities achieves 92.1% accuracy on SNLI.
Read the full abstract

All authors Younes Boufouss, Luc Pommeret, Thomas Gerald, Patrick Paroubek, Sophie Rosset

Information Retrieval · Cross-listed from cs.AI

LSREP: A Longitudinal State-Replay Protocol for Evaluating Conversational Memory, with ICE v2 as an Audited Local-First Architecture

Deepesh Sonar

Conversational memory changes during use, so endpoint question answering alone cannot establish how a persistent state accumulates, ages, or incorporates revisions. We introduce LSREP, a Longitudinal State-Replay Evaluation Protocol combining ordered replay, explicit lifecycle schedules, repeated probes, evolving reference answers, and mechanism-fidelity checks. Its architectural case study is ICE v2, a local-first memory middleware with typed stores, retrieval fusion, and dynamic context budgets. The private, single-user instantiation contains 1,985 turns, 219 distinct probes, and 1,211 probe-checkpoint observations across 52 checkpoints. On three ordinary-density datasets, ICE v2 has a near-zero mean quality difference from vector-RAG while selecting 32% fewer fragments but using 6.6% more estimated prompt tokens. A fourth, dense dataset exposes catastrophic failures of the unbudgeted baseline. The fidelity audit limits attribution: procedural retrieval is defective, several mechanisms are unexercised, and graph utility is not established. In a complementary matched public diagnostic, ICE v2 loses decisively to pure vector-RAG on LongMemEval: 50.8% versus 72.8% in the evidence-only oracle and 43.0% versus 69.5% in full-S. Paired differences are -22.0 points (95% CI [-26.6, -17.4]) and -26.5 ([-31.3, -21.8]). Conservative abstention accompanies severe multi-session and temporal failures. ICE uses less context in this diagnostic, establishing a quality-cost trade-off rather than superior efficiency. Together, replay, fidelity auditing, and public endpoint testing expose distinct failure modes that neither architectural descriptions nor aggregate scores identify alone.
Read the full abstract

Information Retrieval · Cross-listed from cs.CL

Quantifying Organizational Environmental Action from Web Data and Large Language Models

Quinn Reynolds, Daniel Shore, Vianey Leos Barajas et al. (+2 more)

Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because relevant information can be dispersed across multiple webpages and is primarily communicated through unstructured text. We present a scalable computational framework for transforming organizational web content into structured measures of environmental action and demonstrate the approach using Jewish congregations in the United States. We constructed a national database of 4,964 congregations by integrating multiple geospatial, knowledge-base, directory, and manually reviewed sources. Of these, 2,657 had active websites that were successfully crawled, producing a corpus of 154,454 webpages. We compared three approaches for detecting environmental actions: keyword retrieval followed by large language model (LLM) classification, semantic vector retrieval followed by LLM classification, and direct LLM classification classification without preliminary retrieval. Agreement with an expert human reviewer was lowest for keyword retrieval ($\kappa$ = 0.26), higher for semantic vector retrieval ($\kappa$ = 0.42), and similar for direct LLM classification ($\kappa$ = 0.40). Although semantic retrieval achieved the highest agreement, its retrieval recall was 0.87, indicating loss of relevant content before classification. Applied to the complete corpus, direct LLM classification identified at least one environmental action at 1,398 congregations (53%), providing greater coverage than either retrieval-based approach. These results demonstrate that preliminary retrieval can reduce computational cost but may exclude relevant information before it reaches the classifier. The framework provides a reproducible approach for extracting organization-level environmental information from unstructured web content that can be adapted to other institutions.
Read the full abstract

All authors Quinn Reynolds, Daniel Shore, Vianey Leos Barajas, Tanhum Yoreh, Meredith Franklin

Information Retrieval

AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale

SungGeun Kim, Abhinav Narain and Daniel Nemirovsky

How and why does a recommender system fail the users it serves? Oftentimes, practitioners are left to improve their algorithms based on a combination of feedback from stakeholder teams, domain expertise, and insights from data analyses. Yet the nuances of how and where recommendations perform well or poorly for end users are difficult to discern from aggregate quantitative metrics. Whereas these metrics provide a high-level and incomplete picture, further granularity into the quality of recommendations and their patterns requires reasoning with domain understanding and objectivity, at scale. We contemplate this complex conundrum and describe a method and implementation that uses the latest AI agentic advances to provide actionable diagnoses and improvements for production recommender systems. We present AURA (Agentic Understanding and Refinement of recommender Algorithms), an end-to-end agentic system that performs qualitative evaluation at scale and can then generate improvements to our algorithms at the code level. Specialized agents read production engagement logs, from thousands of sessions to millions, and surface patterns and examples of how the recommender fails real users. The next step uses those diagnoses and context about the recommender's own code, data, and training pipeline to propose and implement refinements grounded in that codebase. We report the system design, initial tests on production data from two large consumer platforms at a major media-streaming company, safeguards, operational learnings, and early results toward a self-improving recommender system. Finally, the diagnostic gap AURA closes is not specific to streaming. The architecture is built to transfer: every domain-specific element enters through the configuration layer that already ported it between our two platforms. We map it concretely to e-commerce and online-retail recommendation.
Read the full abstract

Information Retrieval

Measuring Decision-Scale Use in Tool-Augmented LLMs: A Contrastive Urban Benchmark

Ray Chen, Vivian Wong and Christan Grant

Urban decision-support often asks whether activity is unusually high or low for a specific place, not which place has the larger raw count. Twenty pickups in a quiet neighborhood can be more abnormal than 180 at an airport. We introduce URBANCONTRASTIVEQA, a benchmark that asks whether tool-augmented language models can make this baseline-relative comparison. Each item pairs two urban situations from public mobility data in NYC, Chicago, and Seattle, labeled by how far current activity deviates from that place's historical baseline. We evaluate six instruction-tuned models under five tool-output formats. With only raw counts, models often pick the larger number even when it is less abnormal for its zone. Server-computed baseline scores and ordinal labels raise accuracy, but gains vary by model. For heterogeneous urban feeds, tool interfaces need to expose local baselines, not just activity volumes. We release the pair bank, labels, scoring scripts, and data card.
Read the full abstract

Information Retrieval

ReliGRec: Reliability-Oriented LLM-Based Generative Recommendation via User-Risk-Aware Prompt Routing

Haoran Yang, Fei Chen, Yutian Xiao et al. (+1 more)

User behavior in real-world recommender systems is heterogeneous. While some users exhibit coherent preferences, others show abrupt interest shifts, bursty interactions, excessive repetition, or inconsistency with collaborative neighborhoods. Such deviations may arise from benign variation or manipulation, including shilling attacks, but do not alone establish malicious intent. Existing robust recommenders exploit user-risk signals through training-time reweighting or graph aggregation, whereas adapting generation to estimated user-level weak risk remains underexplored in LLM-based generative recommendation. We propose ReliGRec (Reliability-oriented Generative Recommendation), a weakly supervised framework whose name denotes its design goal rather than a supervised reliability variable. ReliGRec derives user-level weak-risk proxy labels from review-feedback signals for a subset of users and represents sequential behavior and collaborative context using a Behavior Token and temporal Graph Tokens, respectively. A Dual-View Weak-Risk Estimator fuses the representations to produce a user-level weak-risk score that selects a Simple or Cautious Prompt at inference. The Cautious Prompt is designed to encourage attention to stable, collaboratively supported evidence while reducing overreliance on isolated, short-term, or repeated interactions. The Behavior Token affects generation through weak-risk estimation and routing, whereas the aggregated Graph Token provides collaborative context for next-item Semantic ID generation. ReliGRec thus turns weak-risk estimation from an auxiliary prediction into a generation-time control signal. Experiments report competitive recommendation and weak-risk proxy-label prediction, while routing analyses characterize the recommendation-quality and inference-cost behavior of weak-risk-guided prompting.
Read the full abstract

All authors Haoran Yang, Fei Chen, Yutian Xiao, Jiahao Liang

Information Retrieval

Predicting Partial Answer Quality and Utility in Agentic Retrieval-Augmented Generation

Fangzheng Tian, Debasis Ganguly and Craig Macdonald

Agentic Retrieval-Augmented Generation (RAG) has become a promising paradigm for multi-hop question answering, where a reasoning model iteratively issues queries to a retriever and incorporates newly retrieved context into subsequent reasoning steps. While this iterative process can improve final answer quality, current evaluations of agentic RAG largely focus on end-to-end outcomes and provide limited visibility into how a model's answer state changes during generation. In this work, we introduce an in-trajectory probing framework to study intermediate answer states in agentic RAG. Specifically, after each retrieval-reasoning iteration, we force an agentic model to stop reasoning and generate an intermediate answer based on its current state. This allows us to define two iteration-level measures: partial answer quality at each iteration, and partial utility as the change in partial answer quality across iterations. Our analysis across multi-hop QA benchmarks reveals that partial answer quality often plateaus before natural termination, with many later iterations contributing only small measurable improvements. Accordingly, we formulate two prediction tasks, partial answer quality prediction and partial utility prediction, and study trajectory-derived signals from intra-iteration, inter-iteration, and query-iteration perspectives. Experiments show that partial answer quality is more predictable than partial utility, with supervised models achieving Pearson's r above 0.43 for quality prediction. Finally, using predicted answer quality and utility for early stopping reduces average iteration count by about 11% while preserving about 98% of the final answer quality achieved by natural stopping.
Read the full abstract

Information Retrieval

PCap: Personalized Retrieval-Stage Diversity Capping in Facebook Marketplace

Guangchao Yuan, Janis Fuh, Christopher Choate et al. (+8 more)

We propose a personalized capping framework (PCap) to improve the diversity in Facebook Marketplace by introducing user-level diversity constraints at the retrieval stage. PCap models individual diversity preferences using Shannon entropy-based scoring, segments users into diversity buckets, and applies personalized category caps during multi-source candidate retrieval. To navigate the high-dimensional parameter space of per-bucket caps, we leverage an automated online optimization method called Parameter Tuning Sequence. Large-scale online experiments demonstrate that PCap significantly improves users' browsing experience shown in engagement metrics. This work provides practical insights into integrating personalized diversity into industrial retrieval systems.
Read the full abstract

All authors Guangchao Yuan, Janis Fuh, Christopher Choate, Xun Tang, Wenqi Zhu, Chengyi Zhang, Pavan Kumar Paalya Chandrashekar, Jiang Han, Jiangyuan Li, Hongyan Wang, Shuting Wang

Monday 14 September

Information Retrieval

Balancing Trial and Reorder: A Hybrid Sequential Transformer-GBDT Ranker for On-Demand Delivery

Marcel Kurovski, Attila Nagy, Steffen Klempau et al. (+1 more)

On a delivery platform, personalized store ranking greatly influences what users find and order. Unlike digital-only domains, candidate stores are local and bound by real-time availability and delivery operations. One central modeling tension is between surfacing new stores for trial and preserving ranking quality for sessions with reorder intent. We present Universal Venue Ranker (UVR), a production system deployed at Wolt that pairs a bidirectional transformer encoder for sequential user modeling with a GBDT ranker integrating contextual, user, and store features. Trained across all stores and domains of a country while enforcing local delivery constraints at inference, UVR replaces four previously separate ranking models (three for restaurants, one for retail) with a single unified system. Label smoothing and trial-biased sample weighting steer the model toward new stores, lifting offline trial MRR by +12% to +30% over production while regressing reorder MRR in five of six countries. These regressions leave Global CVR, our core online metric, which blends trial and reorder sessions, statistically unchanged. We validate UVR in three consecutive A/B tests, the first two across Wolt's largest operating markets and the third spanning all operating countries and both domains. UVR V1 delivers +5.5% Merchant Trial Rate and +0.16% Global CVR over the previous production ranker; V2 adds a further +0.45% Merchant Trial Rate on top; and V3, our cross-domain unification of the restaurant and retail rankers, adds a further +1.31% Retail Merchant Trial Rate, together accounting for substantial incremental gross order value and a materially simplified serving stack.
Read the full abstract

All authors Marcel Kurovski, Attila Nagy, Steffen Klempau, Aleksandr Fedintsev

Information Retrieval

Where Post-Training Quantization Breaks Text Embedders: A Measured Map Across Four Embedder Families

Hyojung Han

Weight-only post-training quantization is the cheapest way to shrink a retrieval embedder, and the received advice for applying it – protect the embedding table, allocate bits by module sensitivity, prefer a ranking-aware objective over weight reconstruction – was carried into LLM quantization largely intact. We test that advice on retrieval embedders directly, quantizing five checkpoints from four architecture families across a grid of bit widths and group sizes, and isolating the embedding, attention and feed-forward blocks at each width. Every heuristic fails to transfer as stated. The embedding table never emerges as the dominant isolated protection priority in any family, despite being the largest tensor in several of them. Module sensitivity does not survive as a transferable ordering: at INT4/g16 the spread between modules is too small to allocate against, at INT3 the ordering becomes family-dependent and joint damage stops being the sum of its parts, and at INT2 comparable reconstruction error accompanies retention ranging from 1.3 to 65.9 percent of full precision. A cheap reconstruction proxy is useful for screening uniform bit widths but substantially less reliable for choosing which tensors to protect; its apparent strength across the whole grid is a range-extension artifact. A distilled 109M student at INT3 holds 78.04 NDCG@10 in 68.4 MB and dominates the extreme-PTQ arm of its own 0.6B teacher, 297.9 MB at 64.46, on both size and quality – but only inside the task it was distilled for. Sizes are byte counts of files that exist rather than arithmetic estimates, and the measurement repository carries the byte provenance for every one of them.
Read the full abstract

Information Retrieval

Evaluating Brand Retrieval and Ranking in Large Language Model Recommendations

Edward Malthouse, Kun-Yu Lee, Jing Yang et al. (+2 more)

Large language models (LLMs) are increasingly used for product recommendation, but evaluating their recommendations presents challenges that differ from conventional information retrieval and recommender systems. LLMs can generate recommendations without an explicit candidate set, and repeated responses to the same query can produce different brands and rankings. We introduce a framework for evaluating open-ended LLM brand recommendations that defines the competitive set independently of model outputs and estimates recommendation prevalence and prominence through repeated sampling. We operationalize these constructs using Brand Recommendation Probability (BRP@$k$) and Mean Reciprocal Rank (MRR@$k$), and apply the framework to six LLMs across five product categories. Category-only queries reveal substantial omission of established brands and limited evidence that recommendation prominence follows conventional brand popularity. Instead, prominence is associated with broader marketplace-visibility signals, particularly search interest and online brand conversation. Needs-based queries show that contextualizing users' goals and constraints changes which brands are retrieved, while diagnostic positioning probes demonstrate that brands omitted from ordinary recommendations can remain conditionally retrievable when distinctive cues are supplied. These findings highlight the need to evaluate LLM recommendation as a stochastic retrieval-and-ranking process rather than from individual generated lists. We provide open-source software and data to support reproducible evaluation of LLM-generated brand recommendations.
Read the full abstract

All authors Edward Malthouse, Kun-Yu Lee, Jing Yang, Sanchary Pal, Xueyan Feng

Information Retrieval · Cross-listed from cs.CL

CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question Answering

Sumit Barua, Guan Hong, Halil Dursunoglu et al. (+2 more)

Retrieval-augmented generation (RAG) can improve access to complex information; however, retrieving evidence alone does not ensure that answers are grounded, citation-valid, or appropriately refused. This paper introduces CiteGuard-RAG, a validation-centered AI system for evidence-grounded question answering. The system integrates hybrid semantic-lexical retrieval, citation-constrained generation, sentence-level grounding validation, and single-pass regeneration. Validation is used at runtime to determine whether a candidate answer should be accepted, refused, or regenerated before final delivery. CiteGuard-RAG is evaluated on 400 questions across a controlled housing-law dataset, PrivacyQA, and CUAD. In the controlled evaluation, it achieves 99.1% retrieval accuracy, 98.3% grounded-answer accuracy, and 98.3% citation validity, with no validation-detected hallucinations. Ablation results show that grounded-answer accuracy drops sharply when validation is removed, even when retrieval accuracy remains unchanged. External evaluation shows that while citation validity remains strong, evidence utilization, span alignment, and refusal calibration become harder under domain shift. These findings indicate that trustworthy RAG systems require explicit validation between retrieval and final answer delivery. CiteGuard-RAG provides a practical architecture for linking retrieval, generation, citation checking, abstention, and regeneration in high-stakes information access.
Read the full abstract

All authors Sumit Barua, Guan Hong, Halil Dursunoglu, Charles Rodgers, Alvis Fong

Information Retrieval

IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English

Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truica et al. (+1 more)

Our team, VANGUARD, presents IROH (Insightful Ranking of Humor), a three-stage retrieval system for JOKER Task 1 English at CLEF 2026, achieving first place on the leaderboard with 0.6347 MAP. Our pipeline combines hybrid sparse-dense retrieval, cross-encoder reranking, and a LoRA-adapted Large Language Model judge ensemble. We employ Gemma 4 to generate query-aware rationales under two prompt strategies, generic and typed, and produce up to four types of structured hard negatives for training data construction. Through an ablation across three cross-encoder architectures, four dense embedders, and eight judge configurations, our key findings are threefold: (1) the rationale-distilled judge is the primary driver of ranking quality, whereas appending rationales to the first-stage index contributes negligibly; (2) structured hard negatives degrade generalisation in nearly all configurations despite inflating local validation scores; and (3) across the components we ablate, the lighter, better-calibrated model is competitive with or stronger than its larger counterpart, with the generic-rationale Qwen2.5-7B judge (0.6055 MAP) outperforming every Gemma-4-31B configuration, and the advantage of generic over typed rationales is concentrated almost entirely in the smaller model.
Read the full abstract

All authors Ana-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truica, Elena-Simona Apostol

Information Retrieval

Self-Evolving Memory for Generative Recommendation

Xinyu Lin, Zhuosong Jiang, Zixiao Suo et al. (+12 more)

Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evolve over time, making self-evolving an essential capability for generative recommender systems. Existing evolving strategies, such as continual retraining and distillation-based adaptation, directly update the shared model parameters using streaming interactions. Nevertheless, we find that directly applying such strategies to generative recommendation introduces a critical issue, termed evolution conflict. Specifically, heterogeneous preference shifts from different users are optimized within a fully shared autoregressive parameter space, causing dominant behavioral patterns to progressively dominate the model evolution process while underrepresented patterns become increasingly overlooked. To address this issue, we propose a self-evolving memory paradigm for generative recommendation, aiming to enable effective evolution across heterogeneous behavioral patterns. We further identify three key principles for effective self-evolving recommendation systems, including isolated memorization, reinforced evolution, and scalable application. Guided by these principles, we develop LION, a simple yet effective framework centered on a sparse Key-Value memory layer. Specifically, LION introduces sparse memory activation to isolate the evolution of different behavioral patterns, while a consolidation loss is designed to reinforce the learning of underrepresented preference dynamics during continual adaptation. Extensive experiments on diverse real-world datasets demonstrate the effectiveness of LION under various continual evolution settings (e.g., per-period evaluation, user/item group evaluation, and evolution convergence analysis). The codes are released at https://github.com/JazyJiang/Self-Evolving-Memory-for-Generative-Recommendation.
Read the full abstract

All authors Xinyu Lin, Zhuosong Jiang, Zixiao Suo, Siqin Wang, Hanqing Zeng, Hanchao Yu, Yinglong Xia, Jiang Zhang, Aashu Singh, Fei Liu, Wenjie Wang, Fuli Feng, Yang Song, Qifan Wang, Tat-Seng Chua

Information Retrieval

The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrieval

Jamie Holdcroft, Abdelrahman Abdallah and Adam Jatowt

Many production RAG systems implement retrieval abstention by thresholding raw similarity scores, implicitly treating score magnitude as a confidence signal. We demonstrate that this practice degrades systematically as queries require reasoning beyond semantic matching. Across 11 retrieval architectures and 28 datasets, neural retrievers consistently assign high similarity scores to semantically related but constraint-violating documents, causing magnitude-based thresholds to collapse toward near-random abstention performance on logical and temporal reasoning tasks—a failure we term the Magnitude Mirage. To address this without computationally expensive alternatives, we conduct a large-scale empirical study of six zero-cost Query Performance Prediction (QPP) metrics across three cognitive tiers: semantic matching (BEIR), logical reasoning (BRIGHT), and temporal reasoning (TEMPO). Our central finding is that the key improvement comes from abandoning magnitude in favor of score-distribution signals: the gain from this shift exceeds the differences among distributional alternatives by a factor of 5-10$\times$. In particular, Score Gap ($s_1 - s_k$) and a practical adaptation of Score Magnitude and Variance (LSMV) improve abstention AUROC by up to 0.16 in settings where magnitude-based confidence provides little discriminative power. These methods require no additional inference, retraining, or latency, making them a practical zero-cost replacement for magnitude thresholding in deployed RAG systems.
Read the full abstract

Information Retrieval

Beyond Retrieval: Scaffolding Children's Online Learning

Diletta Micol Tobia, Hrishita Chakrabarti, Maria Soledad Pera et al. (+1 more)

Children increasingly turn to online information access systems that are primarily designed for the mainstream population, e.g., adults, but possess a limited understanding of how these systems work, contributing to their unstructured and ineffective search practices. This lack of knowledge can hinder their curiosity and the development of critical search skills. Grounded on the existing literature of both child-oriented Information Retrieval and Human Computer Interaction, our work positions children as active participants in the search process, framing it as a scaffolded learning experience rather than a simple retrieval task.
Read the full abstract

All authors Diletta Micol Tobia, Hrishita Chakrabarti, Maria Soledad Pera, Monica Landoni

Information Retrieval

Benchmarking Embedding Models for ESG Data

Motaz Saad, Veronica Cretì, Ivan Gentile et al. (+2 more)

The use of Environmental, Social, and Governance (ESG) data is fundamental for modern corporate accountability, sustainability reporting, and financial decision-making. Embedding models have emerged as a powerful approach for transforming unstructured ESG text into numerical representations suitable for downstream natural language processing (NLP) tasks. However, their effectiveness in these ESG-specific tasks has not been systematically studied. In this paper, we construct a benchmark dataset specifically tailored to the ESG domain. We benchmark fourteen models, both open-source and closed-source embedding models, comparing their performance with respect to retrieval, and Retrieval-Augmented Generation (RAG). The results demonstrate performance variations across different models, with Qwen3-based models achieving the highest overall performance. This study provides practical insights into which models are better suited for ESG RAG tasks.
Read the full abstract

All authors Motaz Saad, Veronica Cretì, Ivan Gentile, Kianna Kazemi, Antonella Longo