Peer Revenue Impact factor: volatile

Papers

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

Computer Science Information Retrieval

cs.IR Watch Information Retrieval

Thursday 6 August

Information Retrieval · Cross-listed from cs.HC

Cleo: A Transparent and Controllable Chatbot for Conversational Commerce

Kevin Schott, Jan Lattenkamp, Daniel Hienert et al. (+1 more)

We demonstrate Cleo, a transparent and controllable conversational product advisor that addresses the challenges of opacity, unpredictability of LLMs, and the complexity of comparisons in conversational commerce. With our chatbot system, we make four contributions: First, we introduce transparency by prompting the LLM to reflect on interpreted user needs, while an auditable ranking mechanism reveals loss values per attribute, explaining ranking decisions. Second, we propose controllability through a hybrid architecture separating deterministic ranking from language generation. A ranker applies categorical filters and numeric loss functions over 3,638 product specifications. Meanwhile, a constrained LLM generates grounded descriptions constrained to catalog evidence, thus mitigating the risk of hallucinated or persuasive content. Third, we provide decision support in the form of natural-language comparisons and a highlights feature. These aim to reduce mental workload by contextualizing specifications relative to user needs. Fourth, we contribute an extensible experimental system for IR and HCI researchers, as well as practitioners of conversational search and recommendation. Unlike traditional faceted search or opaque LLM-only recommenders, our approach allows for fluid conversation while maintaining algorithmic transparency. In a live demonstration, attendees will experience information needs elicitation and reflection, conversational refinement with real-time re-ranking, inspection of per-attribute loss explanations, and AI-generated multi-item comparisons. The system aims to advance the design of transparent and controllable conversational systems that provide support for decision-making during online product search.
Read the full abstract

All authors Kevin Schott, Jan Lattenkamp, Daniel Hienert, Dagmar Kern

Information Retrieval

Is Personalized Modality Weighting Actually Personalized? A Controlled Audit of Per-User Weighting Claims in Multimodal Recommenders

Jingyuan Zheng, Xin Zhang, Yang Gu et al. (+6 more)

Per-user modality weighting is deployed at billion-user scale in multimodal recommenders, through user modality-strength vectors, attention gates, meta-weight hypernetworks, and low-rank guided weights, each claiming a ranking gain from user-specific modality preference. Yet, to our knowledge, prior evaluations do not isolate a genuinely user-specific signal from a global modality weight plus model capacity. We audit this family with a two-contrast audit principle, reducing six implementations onto one shared collaborative backbone and measuring a utility gap (real-GM) against a single global modality weight and an identifiability gap (real-shuf) against an eval-time permutation of the user-weight binding. Across three independent short-video corpora, a single global weight already delivers nearly all of the content gain (+1.9/+3.6/+3.5pp over a no-modality baseline, p < .001). Making the weight per-user adds no consistent utility: no implementation wins on all corpora and metrics, and the few positive gaps are small (<=0.9pp) and flip. The shuffle control is necessary but not sufficient, since real-shuf reaches +128% of the content gain for heads that simultaneously lose to the global weight. We trace this dissociation to gates reading the shared collaborative embedding: decoupling the gate input collapses the inflated real-shuf to near zero while the utility conclusion stands. A monotone signal-implant dose-response (capture AUROC rising from 0.57 to 0.89 and from 0.64 to 1.00) verifies the harness would detect user-specific structure if present, and every finding replicates on a fourth, cross-domain e-commerce corpus. We propose reporting real-GM alongside real-shuf as a minimum evidentiary standard for personalization claims.
Read the full abstract

All authors Jingyuan Zheng, Xin Zhang, Yang Gu, Dongjing Wang, Yuxiang Wang, Xudong Shen, Haiping Zhang, Youhuizi Li, Dongjin Yu

Information Retrieval · Cross-listed from cs.LG

Align-RAG: Alignment Is All You Need for TSFM In-Context Learning

Mohammad Asadi, Soheil Hor, Bardiya Akhbari et al. (+6 more)

Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones cannot dynamically incorporate retrieved context on their own. We show this assumption is unnecessary. We introduce Align-RAG, a training-free method that applies a closed-form per-pair amplitude rescaling and integer-lag phase shift to retrieved past-future windows before they enter a frozen backbone's context. With no learned parameters, Align-RAG outperforms the state-of-the-art trained retrieval adapter on a frozen Chronos-Bolt on all seven datasets of the standard benchmark (avg -3.75% MSE), showing that the gains previously attributed to learned fusion are recoverable without any training. Align-RAG further improves zero-shot MSE on four additional frozen TSFMs with various architectures by 2.5% to 13.7% per backbone with no per-backbone tuning. To probe why alignment helps, we compare the frozen backbone's prediction shift under aligned demonstrations to the closed-form ridge prediction shift on the same pairs. We find that aligned demonstrations induce prediction shifts that track a closed-form ridge predictor on the same pairs, with a future-shuffle control ruling out a futures-averaging account. Together, these results indicate that frozen TSFMs already support dynamic in-context use of retrievals, and that closed-form alignment should be the default baseline for retrieval-augmented forecasting before any fusion module is trained. Code available at: https://github.com/masadi-99/align-rag
Read the full abstract

All authors Mohammad Asadi, Soheil Hor, Bardiya Akhbari, Jack W. O'Sullivan, Tahoura Nedaee, Layne C. Price, Raviteja Anantha, Euan Ashley, Ehsan Adeli

Information Retrieval

omni-macos: On-Device Omni-Modal Search on Apple Silicon

Han Xiao

We present omni-macos, a search engine that embeds text, code, documents, images, audio and video into one representation space and runs its encoder, index and store on the Mac that already holds the files, so the files, the queries and the vectors stay on that machine. It keeps a background indexer and an interactive search box responsive on one shared device. Each distinct chunk is embedded and stored once, indexer work is split into smaller units while the user types, queries scan a one-bit replica of the index and rescore a shortlist exactly, and one memory setting bounds every allocator that draws on unified memory. We measure omni-macos on five Macs spanning an eightfold range of accelerator width and a thirty-twofold range of memory. omni-macos is open source under Apache 2.0 at https://github.com/hanxiao/omni-macos.
Read the full abstract

Information Retrieval

EXCISE: Query-Side Exclusion for Late-Interaction Retrieval

Mohammed Ali, Abdelrahman Abdallah and Adam Jatowt

Late-interaction retrievers handle exclusion queries poorly. When a user asks for X but not Z, the additive MaxSim score promotes documents covering Z, a problem we call exclusion inversion. We show that no readout of the frozen vectors recovers the constraint, because the difficulty lies in identifying the excluded topic, which depends on the query alone. EXCISE operates at query time and corrects the inversion while leaving the index frozen. Two query-side modules totalling 1.5M parameters identify the topic and re-embed a 100-document shortlist, and a parameter-free rule demotes candidates matching that topic. Across six collections and three backbones, EXCISE is the strongest system in all eighteen backbone-collection cells against that backbone's own frozen and fine-tuned baselines. It raises exclusion success@10 on ExcluIR from 0.058 to 0.691 and raises Boolean NOT accuracy from 0.25-0.29 to 0.90-0.92. Pooled over 1,860 queries, it outperforms every fine-tuned cross-encoder, each of which loses no-harm nDCG@10, whereas EXCISE matches its frozen baseline on its strongest backbone. We release X-BENCH, a tiered benchmark of explicit, implicit, and compound exclusions with no-harm and Boolean controls.
Read the full abstract

Information Retrieval

An Ontology-Based Framework for Student Profiling and Content Personalization in Higher Education

José Luiz M. Morais, Arlindo F. da Conceição, Cacilda Encarnação Augusto Alvarenga et al. (+1 more)

The expansion of access to Digital Information and Communication Technologies and the offer of distance or semi-distance education courses that make use of virtual learning environments brought changes in the teaching and learning processes, requiring that the student be even more protagonist in this process. The present study aimed to identify important aspects to be considered in the implementation and improvement of self-paced learning and e-learning in higher education courses, with the purpose of rethinking pedagogical models of courses offered at a distance so that they reach even more of your learning objectives. The research is characterized as qualitative, of bibliographic nature, and discusses techniques to monitor and record, electronically and automatically, the results of the process and learning. The importance of processes that store and manage the student's profile is highlighted, both in terms of content and forms of access. The article proposes the use of ontologies to store information about the educational process and presents a computational architecture for this purpose.
Read the full abstract

All authors José Luiz M. Morais, Arlindo F. da Conceição, Cacilda Encarnação Augusto Alvarenga, Daniela Musa

Wednesday 5 August

Information Retrieval · Cross-listed from cs.HC

Weather- and Location-Aware Agentic Dining Recommendation: Leveraging LLM World Knowledge for Region-Sensitive Contextual Reasoning

Kadharmoideen Fadurudeen

Context-aware recommender systems have long recognized that factors such as location, time, and weather shape where and what people choose to eat. Existing weather-aware food and point-of-interest recommenders, however, typically treat weather generically – mapping conditions to preferences through hand-crafted rules or specially trained context models – and do not capture that the culturally appropriate response to weather is itself region-specific: a rainy evening calls for hot tea and fried snacks in one culinary culture and for very different comfort food in another. Encoding such weather-by-region-by-cuisine interactions as explicit rules or training data is brittle and does not scale. We present a weather- and location-aware agentic dining-recommendation system that takes a different approach: a large language model (LLM) orchestrates tools for location and weather retrieval and then reasons in natural language over the combined context, drawing on the cultural and culinary world knowledge already latent in the model to produce region-sensitive, weather-appropriate recommendations without per-region rule tables or specialized training. We describe the agent architecture, the tool-orchestration flow (Google location services and a weather service feeding an OpenAI LLM), and the reasoning mechanism, and we report on a working prototype that was implemented and briefly deployed end-to-end. We discuss design trade-offs – cost, latency, ambiguity handling, and fallbacks – and we are explicit about limitations, including the absence of a formal user study and the risk of cultural stereotyping in locality-based inference. The contribution is architectural: a simple, extensible pattern for incorporating environmental and cultural context into agentic recommendation through LLM reasoning rather than engineered rules.
Read the full abstract

Information Retrieval

A Mechanistic Analysis of Gender Sensitivity in Dense Retrieval Models

Catherine Chen, Maarten de Rijke and Carsten Eickhoff

While gender bias in dense retrieval models is well documented, with prior work showing that models often score male-gendered documents higher than female or neutral variants, the internal mechanisms producing these disparities are poorly understood. In this paper, we mechanistically analyze bi-encoder models to localize gender sensitivity, finding that the signal originates in input embeddings and propagates through a small set of late-layer attention heads that carry both gender and term-matching signals. Guided by these findings, we test steering interventions at both identified points and find distinct effects: embedding-level steering non-specifically neutralizes score differences, while attention-level steering produces directional shifts. Our findings provide a mechanistic basis for targeted debiasing and highlight the challenge of disentangling gender from relevance signals in shared model components.
Read the full abstract

Information Retrieval · Cross-listed from cs.DB

Filtered Vector Search in a Disaggregated Lakehouse: Composing Table-Format Pruning with Per-File ANN

Rakesh Jain, Thomas Griffin and Syed Zawad

Approximate nearest-neighbor (ANN) search increasingly runs alongside structured data - "find the 10 nearest documents where tenant='acme' AND lang='en'" - yet similarity and filtering are usually bolted together: a specialized vector index for one, a separate filter step for the other. We ask what happens when both live inside an open lakehouse table (Apache Iceberg over Parquet on object storage), where the engine already owns a mature file-pruning stack (partition pruning, zone-maps, a bitmap index). We embed an IVF index in place in each Parquet file's footer and make filtered vector queries fast not with a new filtering algorithm but by composing the table's existing file pruning with per-file ANN: the planner prunes data files by the predicate first, then runs IVF only over the survivors. The index is built distributed and non-destructively - a metadata-only Iceberg replace that every other engine still reads - and a rendezvous-hashed per-file cache keeps object-store read latency from swamping the algorithmic win. The payoff comes entirely from file pruning. On an 11.5M x 768 table, warm IVF search is ~32x faster than brute force at recall@10 >= 0.90, a selective predicate having pruned 355 of 444 data files before ANN runs; on 5M real IBM Granite embeddings, a filter arriving across a join prunes four of five region partitions and runs nearly two orders of magnitude (~94x: 14.7 s -> 157 ms) faster than the query-time join at identical top-k, once the reduction is materialized into a region-partitioned layout. We characterize when the composition pays off - it requires file-level locality on the filter column, and the residual predicate is only safe to push into the search over a provably pure (partitioned) column, not a merely sorted one - and report the failure modes we hit bolting ANN onto a lakehouse engine.
Read the full abstract

Information Retrieval

Robustness and User-Perceived Value of Popularity Calibration in Music Recommendation: A User Study

Oleg Lesota, Gustavo Escobedo, Bruce Ferwerda et al. (+4 more)

Popularity calibration in recommender systems has been studied both as a form of user-centered personalization and as an indicator of popularity bias. Most existing work evaluates calibration through offline metrics, often assuming that users prefer recommendation lists whose popularity distribution matches their historical consumption profile. However, user studies on calibration remain limited, and existing findings suggest that calibrated recommendations do not necessarily have a strong effect on user experience. Moreover, although prior work has shown that calibration metrics can correlate with users' perceptions of recommendation lists, the robustness of this relation remains unclear under different levels of item familiarity and incomplete user-history information. In this work, we study the perceived value and measurement reliability of popularity calibration in music recommendation. We construct personalized track lists from users' recent listening histories and use a controlled naive recommender to create lists with different popularity compositions: highpop-heavy, lowpop-heavy, and calibrated. We investigate whether users perceive differences between these lists, whether calibrated lists are preferred, how robust JSD-based popularity calibration is under different familiarity and history-availability conditions, and how computational popularity labels align with users' own popularity judgments. Our results show that users perceive differences in popularity composition, but do not clearly prefer calibrated lists. We further find that the relation between JSD and perceived popularity depends on item familiarity, list composition, and available user history, while computational and user-judged popularity labels only weakly align. These findings contribute to a more critical understanding of popularity calibration as both an offline metric and a user-facing construct.
Read the full abstract

All authors Oleg Lesota, Gustavo Escobedo, Bruce Ferwerda, Simone Kopeinik, Dominik Kowald, Elisabeth Lex, Markus Schedl

Information Retrieval

Cross-platform epistemic verification for improving factual reliability in AI-generated news summarization

Zhuo Xie and Haoze Ni

This study proposes Multi-source Evidence Consen- sus Verification (MECV), a post-hoc hallucination cor- rection framework for AI-generated news summariza- tion. Instead of depending on a single retrieval channel, MECV aggregates evidence from multiple heterogeneous sources, including the source document, Wikipedia, and open-web retrieval. The framework further incorporates a multi-LLM jury mechanism that estimates factual reliabil- ity through contradiction-aware consensus scoring across verifier models. Claims identified as potentially unsup- ported are revised through iterative minimal-edit refine- ment. The proposed framework is evaluated on the SummEd- its benchmark using GPT-4o-mini and DeepSeek-Chat as the verifier jury, with Qwen-Plus as the orchestra- tor. Experimental results show that MECV improves fac- tual consistency while preserving the semantic structure of the original summaries. The findings further suggest that agreement across heterogeneous evidence sources can serve as a useful signal for identifying factual uncertainty in AI-generated summaries, including in information- sensitive domains such as financial news aggregation. This study contributes to research on trustworthy AI and automated journalism by introducing a multi-source verification framework for hallucination correction and demonstrating the value of consensus-based verification for improving factual reliability in AI-generated news summarization.
Read the full abstract

Information Retrieval

From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents

Zijie Zhuang, Changxin Lao, Pengbo Xu et al. (+13 more)

Research agents increasingly conduct multi-round machine-learning experiments in industrial recommendation settings and retain the resulting trajectories to guide later decisions. Yet a completed trajectory is not automatically evidence: generated artifacts may be unsupported or incomplete, executed rounds may be invalid or confounded, and later modifications may obscure earlier findings. We study trajectory-to-evidence conversion, asking what a completed research process has actually established. We introduce an evidence-grounded framework that couples bounded verification of consequential artifacts with post-execution claim qualification. A context-isolated generate–verify–repair process checks artifacts for evidence violations and missing downstream requirements before release. After execution, validity and attribution checks consolidate evidence across rounds, qualify intervention-level claims as actionable repairs, diagnostic guards, or withheld findings, and preserve admitted claims as auditable records with explicit provenance and applicability boundaries. A hybrid LLM-assisted controller subsequently applies, defers, or rejects records based on available target evidence. Record audits characterize which claims survive qualification, while downstream diagnostics identify affirmative applicability judgment as a bottleneck for the tested controller. Across paper-to-target adaptations, later rounds often improve on the first, while final rounds frequently underperform an earlier best, exposing non-monotonic trajectory evolution. Candidates produced through the complete workflow also yielded positive online lifts relative to deployed baselines.
Read the full abstract

All authors Zijie Zhuang, Changxin Lao, Pengbo Xu, Hanwen Xu, Ruochen Yang, Yingzhi He, Peng Zhang, Jiangxia Cao, Yusheng Huang, Guohong Mu, Jian Liang, Ruiming Tang, Shuang Yang, Zhaojie Liu, Wenwu Ou, Kun Gai

Information Retrieval

BioMedJImpact: A Comprehensive Dataset and LLM Pipeline for AI Engagement and Scientific Impact Analysis of Biomedical Journals

Ruiyu Wang, Yuzhang Xie, Xiao Hu et al. (+2 more)

Assessing journal impact is central to scholarly communication, yet existing resources rarely capture how collaboration and artificial intelligence (AI) research jointly shape venue prestige in biomedicine. We present BioMedJImpact, a large-scale, biomedical-oriented dataset built from 1.74 million PubMed Central articles across 2,744 journals. BioMedJImpact integrates bibliometric indicators, collaboration features, and an LLM-derived AI engagement rate, defined as the proportion of AI-related articles within each journal-year. Specifically, AI engagement rate is extracted through a reproducible three-stage LLM pipeline. We analyze how collaboration intensity and AI engagement rate jointly influence scientific impact across two temporal subsets (2016-2019, 2020-2023). Two main patterns emerge: journals with larger author teams tend to have higher citation impact, while AI engagement rate is positively associated with Impact Factor only in the 2019 subset. To validate the LLM pipeline for deriving the AI engagement rate, we conduct human evaluation, confirming substantial agreement in AI relevance detection and consistent subfield classification. Together, BioMedJImpact provides both a comprehensive dataset at the interface of biomedicine and AI and a validated framework for scalable, content-aware scientometric analysis. Code and dataset are available at https://github.com/JonathanWry/BioMedJImpact.
Read the full abstract

All authors Ruiyu Wang, Yuzhang Xie, Xiao Hu, Carl Yang, Jiaying Lu

Information Retrieval

MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off

Songxin Lei, Kun Ouyang, Weilin Ruan et al. (+4 more)

Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context to downstream models. Existing memory pipelines often rely on hand-crafted heuristics and repeated LLM calls, which can introduce redundant context and high inference cost. We propose MemoryCPT, an end-to-end trainable agent memory pipeline that spans offline memory construction and online query-conditioned context generation. MemoryCPT consists of two stages: Query-agnostic Distillation (QAD), which distills a modular memory-construction pipeline into a compact model using explicit reasoning traces; and Query-aware Retrieval and Summarization (QAR), which combines reciprocal rank fusion (RRF) with a LoRA-based summarizer trained via Group Relative Policy Optimization (GRPO) under a cost-aware reward. We further introduce Quality per Cost (QPC) to quantify answer quality per unit inference cost. Experiments on LoCoMo and LongMemEval show that MemoryCPT improves the cost-performance trade-off over the evaluated baselines, while ablation and sensitivity analyses characterize the contributions of its components and the effects of key design choices.
Read the full abstract

All authors Songxin Lei, Kun Ouyang, Weilin Ruan, Yuqian Wu, Zhijiang Guo, Yushi Sun, Fugee Tsung

Information Retrieval

DEGR: Dual Exploration-Driven Generative Re-Ranking for Adaptive Cross-Request Context Bridging

Binglei Zhao, Xuanhua Yang, Xiwei Zhao et al. (+1 more)

In industrial recommendation systems, the re-ranking stage balances business objectives and diversity for sequence-level optimization while modeling contextual information. However, constrained by fixed upstream supply, existing methods fail to deliver further effectiveness gains, especially under low-quality supply. To overcome this, re-ranking can actively balance immediate and exploratory value, for instance, by prioritizing exploratory exposure under low-quality supply to preserve browsing potential and facilitate serendipitous conversions. Therefore, we propose a Dual Exploration-Driven Generative Re-Ranking (DEGR) method. DEGR adopts a hybrid supervised-reinforcement exploration and optimization paradigm, guided by an exploratory reward model that adaptively balances immediate and exploratory value. The hybrid optimization paradigm integrates three key components: supervised learning, exploration diversity constraint, and adaptive reward-weighted ORPO for preference optimization. Through this dual exploration, the generator ultimately acts as an adaptive cross-request contextual bridge. Offline and online experiments indicate that DEGR outperforms SOTA methods, achieving improvements of up to 1.22% UCTR and 0.20% PV in the JD E-commerce recommendation system.
Read the full abstract

All authors Binglei Zhao, Xuanhua Yang, Xiwei Zhao, Sulong Xu

Information Retrieval

WatchLens: A Configurable Platform for Online Video Recommendation Experiments

Deogyong Kim and Dongha Lee

Studying how video recommender systems shape user behavior requires online experiments that link playback behavior with the recommendation conditions that produced it. Existing user-study infrastructure provides one or the other, but not both within a single experimentation workflow. We present WatchLens, an open-source platform that fills this gap. WatchLens adopts a modular architecture in which user interfaces, content sources, and recommendation policies are independently configurable, with policies assignable separately to the feed and the watch page, while a standardized logging layer attaches the recommendation policy and ranking position to every event at recording time. This design enables researchers to analyze how recommendation policies and ranking positions shape downstream playback behavior, session continuation, and navigation between the feed and the watch page, with the linkage between policy and outcome available in each event rather than reconstructed afterwards. We demonstrate WatchLens with a short-form video case study that holds the interface, feed policy, and content pool constant while varying only the watch-page policy, showing how the platform supports session-level comparison of recommendation effects on real viewing behavior. WatchLens is released as a publicly available, single-server deployable system for reproducible online video recommendation research.
Read the full abstract

Information Retrieval · Cross-listed from cs.CL

Caching for the Future: Scrub Jay Episodic Memory Principles for Agent Memory Systems

Kartikey Singh Bhandari, Aarya Wadhwani, Dhruv Kumar et al. (+1 more)

LLM agents that persist across sessions accumulate stored memories whose validity varies enormously by content type, yet existing memory architectures treat all memories as equally persistent and systematically contaminate retrieved context with outdated facts. We show that per-memory, type-conditioned temporal decay, a property of western scrub jay episodic memory, can be operationalized as an auto-classified coefficient $\pi_i$ in an external LLM-agent memory store, yielding ScrubJay-MEM: each memory is encoded as a jointly-bound What–Where–When tuple with an estimated perishability $\pi_i$ and utility horizon $\tau_i$, retrieved by query-adaptive scoring, and revised retroactively at $O(1)$ LLM calls per update. We introduce the Temporal Generalization Test (TGT), a benchmark with held-out retention intervals and a Generalization Gap (GenGap) metric. On TGT, ScrubJay-MEM is the only retrieval-based system with substantially positive GenGap ($+0.108$); on MemoryAgentBench EventQA-64k it improves F1 by $+2.66$ over Mem0 and $+3.09$ over Qwen3-Embedding-4B under a llm backbone. A decay ablation collapses GenGap by $5.7\times$, establishing type-conditioned decay as necessary for the result. Gains narrow under stronger backbones and reverse on fact-consolidation tasks, scoping the contribution to temporal reasoning over perishable facts.
Read the full abstract

All authors Kartikey Singh Bhandari, Aarya Wadhwani, Dhruv Kumar, Pratik Narang

Information Retrieval

Characterizing the Evolving Landscape of Modern Information Seeking

Shuoqi Sun

Information seeking (IS) evolves, as does the human IS process. Since the rise of Generative AI (GenAI), modern IS has shifted by introducing more interfaces, more complex interactions, and expanded system capabilities. We argue that these changes in modern IS should be systematically examined. This PhD research characterizes the changes in the modern IS process. We use mechanisms, including online crowdsourcing survey experiments, theoretical IS frameworks, and in-lab experiments with neurophysiological signals, to characterize the shifts in modern IS, especially those driven by GenAI. We offer insights into the current landscape of search interface preferences and the cognitive efforts involved in seeking information. We believe this PhD research will contribute to and inform future designs of personalized, cognition-aware IS systems.
Read the full abstract

Information Retrieval · Cross-listed from cs.SD

Towards Robust Version Identification in the Wild: A Dataset, Benchmark, and Fine-Tuning Study

Simon Hachmeier, R. Oguz Araz, Dmitry Bogdanov et al. (+2 more)

Existing datasets for musical version identification (VI) are primarily derived from curated metadata sources such as SecondHandSongs and Discogs, and are therefore dominated by professionally recorded tracks. This leads to a domain mismatch with real-world scenarios, where amateur and user-generated content is prevalent. To address this limitation, we introduce DiVers, a large-scale VI dataset comprising over 1.1 million musical versions, with train-validation-test splits compatible with established datasets such as Discogs-VI-YT, SHS100K, and Da-TACOS. In addition to standard version-level annotations, DiVers provides automatically assigned tags (e.g., instrumental, live) and segment-level predictions indicating the presence or absence of music. We evaluate the proposed dataset by training state-of-the-art VI systems. Our results show that models trained on DiVers achieve substantially improved robustness to acoustically diverse and noisy inputs, while maintaining a stable performance on cleaner, studio-quality benchmarks. We release the dataset metadata, code for its construction, and all experimental pipelines to support reproducibility.
Read the full abstract

All authors Simon Hachmeier, R. Oguz Araz, Dmitry Bogdanov, Robert Jäschke, Xavier Serra

Information Retrieval

Skills Know Their Neighbors: Cluster-Contrastive Capability Pages for Skill Retrieval

Zifei Wang, Wei Wen, Qiang Ji et al. (+1 more)

As skill libraries grow, large language model agents must retrieve reusable skills from candidates that often share the same topic and vocabulary but implement different capabilities. Retrieval is limited not only by the scorer but also by the text being scored: a document may describe what a skill does without stating which similar requests should be routed elsewhere. We formalize a skill's capability as its executable region, the set of queries it can solve, and view its document as a lossy observation of that region. This view exposes a document-imposed component of retrieval error that cannot be removed by improving the retriever alone. We therefore propose Capability Pages, cluster-contrastive skill representations containing a positive trigger $\Tpos$, a negative boundary $\Tneg$, and a discriminative body $B$. An offline compiler compares neighboring skills to write these fields. At inference time, the index uses $\Tpos$ and $B$ for candidate recall, while the router uses $\Tneg$ to reject confusable alternatives. On SRA-Bench, which contains 26{,}262 skills and 5{,}400 questions from six datasets, Capability Pages improve Recall@10 for all five tested retrievers, with a mean gain of $2.94$ points. Adding $\Tneg$ to candidate cards improves end-to-end task success by $3.62$ points on average across four executors and six datasets. A transfer evaluation on Chinese SSL-SkillDiscovery reaches $73.07\%$ MRR@50 using the same encoder across conditions. Capability Pages require no modification to the online models; they improve routing by rewriting the offline skill library.
Read the full abstract

All authors Zifei Wang, Wei Wen, Qiang Ji, Ruizhi Qiao

Information Retrieval

Multi-Objective Ranking for Live-Streaming: Balancing Fresh and Delayed Signals with Segment-Aware Targeting

Xiaoyi Gu, Julia Tavares, Eder Santana et al. (+3 more)

One of the most challenging problems entertainment live-streaming services face in recommendation systems is that user behaviors are sparse and delayed, and interaction data exhibits bias for different user segments. Unlike e-commerce applications where user actions follow linear sequences, live-streaming viewers engage in multiple concurrent behaviors of watching, chatting, following, and spending, each occurring with varying delays. We address these challenges through three key contributions: 1) a delayed window approach that extends feedback collection beyond immediate responses, 2) a multi-model architecture that combines fresh and delayed signals, and a segment-aware targeting module that optimizes ranking scores differently across user lifecycle stages, and 3) Multi-gate Mixture-of-Experts (MMoE) integration that jointly models correlated targets while reducing model parameters by 41.9% compared to independent models. Online A/B testing demonstrates significant improvements, including a +0.09% increase in Daily Active Viewers (DAV), generating millions more annual active viewer days, and +0.56% increase in highly engaged viewers' capped Average Revenue Per User (ARPU). Viewer-segment targeting achieved an additional +0.15% DAV improvement for newer and less engaged viewers, while MMoE enhancement added +0.08% overall DAV and +0.27% new follows. The proposed system processes ranking requests with low latency, providing a scalable approach for balancing multiple business objectives across diverse user populations. In addition, we tested the multi-model architecture on the Twitch mobile live feed and achieved a +1.12% increase in positive user-channel interactions (clicks, follows, and likes), demonstrating applicability beyond the primary use case.
Read the full abstract

All authors Xiaoyi Gu, Julia Tavares, Eder Santana, Carlos Mendoza-Cardenas, Nikita Mishra, Saad Ali

Information Retrieval

The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing

Yuanyuan Shen, Yiren Yan, Wenjie Li et al. (+1 more)

On two-sided content platforms, symmetric two-sided isolation (assigning matched fractions of creators and viewers to isolated treatment and control submarkets) is widely used for creator-side and cold-start experiments because it removes cross-arm marketplace interference. Isolation, however, thins each viewer's candidate catalog, and intuition suggests the resulting engagement cost should fade as the platform grows: a small fraction of a vast catalog is still vast. We show that, in an order-statistics model of engagement, whether this intuition holds depends on the upper tail of match quality. Extreme-value theory yields tail-class loss laws with a sharp dichotomy: for light or bounded tails the loss vanishes as the candidate pool grows, whereas under heavy tails it converges to a size-independent constant, so expanding the candidate pool, even by orders of magnitude, does not asymptotically eliminate the cost. Evidence from two production experiments on a platform with millions of active creators is consistent with this picture: a pure A/A traffic sweep reveals a measurable, depth-graded engagement cost; a one-sided catalog ablation independently shows that per-viewer thinning contributes to the loss; and a tail index calibrated on the small exploration pool predicts an effect consistent with the one observed in the far larger full-catalog ablation. Isolation thus carries a price that experimenters should budget for, like any other cost. We give practitioners a preflight procedure that estimates it before launch, sizes traffic accordingly, and recommends a fallback design when the predicted cost exceeds a chosen tolerance.
Read the full abstract

All authors Yuanyuan Shen, Yiren Yan, Wenjie Li, Chunhui Zhu

Information Retrieval · Cross-listed from cs.CV

CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models

Mukhtiar Ali, Harsh Dubey, Sugam Mishra et al. (+1 more)

Benchmarking video-language models has largely focused on short clips and single-sentence metrics, leaving open whether current systems can generate accurate long-form, paragraph-level descriptions. We introduce CLIP-CC-Bench, an evaluation suite for long-form video description built from 5 hours of movie content segmented into 90-second clips, each paired with an expert-written paragraph-style reference. The evaluation suite employs an ensemble of five state-of-the-art LLM-based embedding models to increase reliability and mitigate single-model bias, and applies two complementary methodologies: (i) coarse-grained semantic matching and (ii) fine-grained semantic matching to compare model-generated descriptions against CLIP-CC-Bench references. Using this framework, we evaluate 17 state-of-the-art video-language models and report both their Borda-aggregated rankings and their average scores on CLIP-CC-Bench. We further quantify the protocol's internal reliability through inter-judge agreement and bootstrap ranking stability. We release standardized evaluation scripts, model outputs, and aggregation tools at https://github.com/Multimodal-Intelligence-Lab/CLIP-CC-Bench to support reproducibility. CLIP-CC-Bench provides a practical evaluation framework for long-form video description, filling a gap left by existing short-clip and QA-only benchmarks.
Read the full abstract

All authors Mukhtiar Ali, Harsh Dubey, Sugam Mishra, Chulwoo Pack

Tuesday 4 August

Information Retrieval

TSG Suggester: Tree-Structured Knowledge-Graph Retrieval for Troubleshooting Guide Recommendation in Cloud Incident Management

Shawn Pan, PavanUttej Ravva, Walt Williams et al. (+5 more)

On call engineers in large scale cloud services work under intense time pressure, yet locating the correct Troubleshooting Guide (TSG) for an incident remains a largely manual, keyword driven process, and prior empirical work finds that guide search consumes a substantial fraction of total mitigation time. We present TSG Suggester, a retrieval system that recommends relevant TSGs directly from an incident description. We evaluate five retrieval strategies: Text Only RAG, Image Augmented RAG, RAPTOR, Tree Structured Retrieval, and our proposed Tree + Knowledge Graph (Tree+KG), on 314 real world incidents spanning 112 unique TSGs drawn from 18 service teams on a production incident management system. Tree+KG converts each guide into a tree that preserves its native section hierarchy, attaches LLM generated problem abstractions to internal nodes to bridge the solution oriented language of guides and the problem oriented language of incidents, extracts a per guide entity knowledge graph, and fuses embedding similarity with entity level matching at query time. Tree+KG attains 54.78% Top 1 and 82.48% Top 5 accuracy, leading every baseline at every cutoff, with an 8.58 point Top 1 gain over text only RAG. Two findings are of independent interest. First, structural alignment dominates: methods that preserve or rebuild document structure outperform flat chunking where precise discrimination matters. Second, and contrary to our initial hypothesis, multimodal enrichment actively hurts. Captioning guide screenshots and injecting the captions costs 22.64 Top 5 points relative to the text only baseline because generic captions dilute embeddings rather than sharpen them. We report error analyses for both results and provide concrete deployment guidance.
Read the full abstract

All authors Shawn Pan, PavanUttej Ravva, Walt Williams, CJ Barberan, Nutan Sahoo, Ziran Min, David Gross, Irene Shaffer

Information Retrieval

Neighborhood-Aware Dual Biomedical Entity Linking

Yicheng Tao and Jie Liu

Biomedical entity linking grounds mentions in clinical and scientific text to entities in a curated knowledge base (KB) with ontological structure, which supports downstream applications such as literature-scale information extraction and patient-record normalization. The task has several challenges at once: the KB contains large numbers of entities, mentions are often ambiguous, and gold labels follow annotation conventions specific to each corpus. To address these challenges, we propose PILOT, a three-stage framework made up of neighborhood-aware retrieval, dual reranking, and score fusion. The retriever injects ontological structure from both the query and KB side, by reformulating mentions and pooling entity embeddings. The retrieved pool is then scored from two complementary views, one over surface forms and one over context, and fused together. PILOT achieves the state of the art on average across five widely-used benchmarks and remains efficient at inference.
Read the full abstract

Information Retrieval

ATLAS: Learning to Recommend Across Unseen Domains

Pervez Shaik, Prosenjit Biswas, Abhinav Thorat et al. (+2 more)

Recommender systems remain domain-bound: a model trained on one interaction environment typically requires retraining or target-domain adaptation before it can operate on a new catalogue. A recommender trained on movies cannot be directly deployed to recommend groceries or video games. Existing approaches mitigate this by transferring restricted forms of recommendation knowledge, adapting to the target domain, or leveraging large language models (LLMs) for transferable representations. We instead ask whether recommendation-specific knowledge learned solely from multiple heterogeneous domains can generalize to entirely unseen domains without target-domain adaptation or language-model pretraining. We introduce ATLAS, a multi-source recommendation domain generalization framework that learns a shared, domain-invariant user-item representation from disjoint source domains, enabling zero-shot recommendation on unseen domains. ATLAS combines a Gromov-Wasserstein alignment that preserves how users relate to one another across domains, an adversarial objective that makes item representations indistinguishable across domains, and residual vector quantization (RVQ) codebooks that compress user and item embeddings into a discrete latent space, capturing hierarchical interaction patterns while suppressing domain-specific variation. Trained on five Amazon domains and applied directly to ten unseen domains, ATLAS outperforms state-of-the-art sequential, graph-based, cross-domain, quantization-based, and LLM-based baselines on most unseen domains, with an average relative gain in HitRate of 24%. Ablations and representation analyses validate each component, and we identify a pronounced source-domain diversity effect: increasing source heterogeneity substantially improves zero-shot transfer. ATLAS establishes recommendation domain generalization as a promising paradigm for zero-shot recommendation.
Read the full abstract

All authors Pervez Shaik, Prosenjit Biswas, Abhinav Thorat, Ravi Kolla, Niranjan Pedanekar

Information Retrieval · Cross-listed from cs.CL

MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning

Martin Böckling, Elizaveta Nosova, Heiko Paulheim et al. (+1 more)

Geospatial reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to navigation and logistics, yet large language models (LLMs) struggle with the required geometric and topological computation despite storing considerable geographic knowledge. Existing benchmarks localize these failures only partially: they are synthetic or smallscale, largely monolingual, and offer limited control over geographic coverage. We introduce MultiGlobeQA, a multilingual benchmark of 46,060 question-answer pairs spanning 14 spatial-function families and 15 answer formats, with execution-based ground truth over three knowledge graphs. It covers 201 countries and territories via income- and density-stratified sampling, with parallel questions in English and 16 additional high- and low-resource languages. Across parametric, reasoning, and agentic settings, LLMs collapse on tasks requiring grid indexing and shape computation, while topological relations and directions fare best. Retrieval and tool use yield considerable gains, yet performance plateaus below two thirds even when gold facts are supplied, indicating that computation, not access to knowledge, is the bottleneck. Models also underperform on low-income regions, a gap that gold facts widen rather than close.
Read the full abstract

All authors Martin Böckling, Elizaveta Nosova, Heiko Paulheim, Andreea Iana

Information Retrieval · Cross-listed from cs.CL

SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG

Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab et al. (+1 more)

We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in our setting, reaching Recall@10 of 1.000 at 1K and 15K. In contrast, an MS MARCO-trained cross-encoder reranker reduces precision on the scientific corpus, suggesting that domain mismatch can outweigh the benefits of stronger query-passage interaction. Generation faithfulness measured with RAGAS increases with corpus scale in our setup. Retrieval evaluation uses pseudo-relevance labels derived from the hybrid system, so we treat the results as controlled comparative evidence rather than a benchmark claim. We release code, indexes, and evaluation outputs to support replication and follow-up studies.
Read the full abstract

All authors Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab, Asab Azad

Information Retrieval

LegalPincite: Multi-level Legal Information Retrieval Dataset

Theresia Veronika Rampisela, Henrik Palmer Olsen and Giovanni Colavizza

A common task in legal Information Retrieval (IR) is to find relevant legal sources from case-law collections. While legal practice often requires pinpoint citations (pincites) to specific case paragraphs, most existing public legal IR datasets lack paragraph-level citation annotations. Yet, publicly available datasets with such information contain data leakage in the query text and exclude paragraphs that are neither citing nor cited from the corpora, creating an unrealistic and oversimplified retrieval setting, potentially leading to inflated performance. To address these limitations, we contribute a large-scale legal IR dataset constructed from Court of Justice of the European Union (CJEU) judgments. The dataset contains: (i) masked case/paragraph queries, with removed citation information; (ii) a corpus that includes all paragraphs; and (iii) case- and paragraph-level ground truth citations, with partial human expert validation. Our dataset supports both the development and rigorous evaluation of legal IR methods, at multiple query-document levels (case-to-case, paragraph-to-case, and paragraph-to-paragraph retrieval). Link to dataset and code: https://huggingface.co/datasets/theresiavr/legalpincite
Read the full abstract

Information Retrieval

SITA: Semantic Interest Tokens for Target-Aware Compression in Long-Sequence Recommendation

Rui Zhou, Bo Chen, Qinglin Jia et al. (+5 more)

As user behavior histories continue to grow on modern Internet platforms, effectively modeling long behavior sequences has become crucial for predicting user interests in candidate items. Existing methods have evolved along two directions. One line dynamically retrieves target-relevant behaviors from long histories, enabling target-aware modeling but requiring target-dependent computation during inference. The other line compresses entire behavior sequences into compact user representations, achieving high efficiency and scalability but sacrificing target-specific adaptation due to target-independent encoding. The key challenge is therefore to enable target-aware modeling while preserving the efficiency and scalability of compressed user representations. To address this challenge, we propose SITA, a target-aware compression framework for long-sequence recommendation. SITA enables target-aware compression by organizing compressed interests into semantic structures through semantic identifiers learned via parallel semantic quantization. Conditioned on the semantic identifier of the target item, SITA adaptively aggregates the corresponding structured interests to construct the target-specific user representation. Extensive experiments on public datasets and a large-scale industrial dataset demonstrate that SITA consistently outperforms representative baselines while maintaining strong scalability, highlighting its strong potential for real-world recommender systems.
Read the full abstract

All authors Rui Zhou, Bo Chen, Qinglin Jia, Jiezhou Ji, Chaoyi Ma, Ruiming Tang, Hao Wang, Enhong Chen