pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

1286 papers in cs.IR · page 14

  1. cs.IR 2026-04-09 reviewed
    GUI agents match outcomes but navigate search differently

    Same Outcomes, Different Journeys: A Trace-Level Framework for Comparing Human and GUI-Agent Behavior in Production Search Systems

    Maria Movin +3

  2. cs.IR 2026-04-09 reviewed
    Automated loop lets support agent skills surpass expert versions

    SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support

    Xingyan Liu +5

  3. cs.IR 2026-04-09 reviewed
    Ensembles lift recommender accuracy 0.3-5.7% at 19-2549% energy cost

    Ensembles at Any Cost? Accuracy-Energy Trade-offs in Recommender Systems

    Jannik Nitschke +2

  4. cs.IR 2026-04-09 reviewed
    Learned graph memory lifts agent retrieval to 82.7 nDCG@10

    Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory

    Saman Forouzandeh +2

  5. cs.IR 2026-04-09 reviewed
    Reinforcement fine-tuning adds step-by-step reasoning to LLM recommenders

    ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning

    Jiani Huang +4

  6. cs.IR 2026-04-09 reviewed
    Probing flags LLM item gaps for selective knowledge fixes

    Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders

    Jaehyun Lee +3

  7. cs.IR 2026-04-09 reviewed
    Graph contexts raise fidelity in personalized review generation

    PeReGrINE: Evaluating Personalized Review Fidelity with User Item Graph Context

    Steven Au +1

  8. cs.IR 2026-04-09 reviewed
    Gradient selection trims data for adapting recommenders

    Efficient Dataset Selection for Continual Adaptation of Generative Recommenders

    Cathy Jiao +9

  9. cs.IR 2026-04-08 reviewed
    Models outperform pipelines on alloy experiment extraction by tracking processing steps

    LitXBench: A Benchmark for Extracting Experiments from Scientific Literature

    Curtis Chong +1

  10. cs.IR 2026-04-08 reviewed
    LLMs pull full experiments from papers 0.37 F1 better than pipelines

    LitXBench: A Benchmark for Extracting Experiments from Scientific Literature

    Curtis Chong +1

  11. cs.IR 2026-04-08 reviewed
    Frontier models top extraction pipelines by 0.37 F1 on alloy experiments

    LitXBench: A Benchmark for Extracting Experiments from Scientific Literature

    Curtis Chong +1

  12. cs.IR 2026-04-08 reviewed
    DCD hierarchy narrows RAG scopes to lift accuracy

    DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation

    Valerii Kovalskii +4

  13. cs.IR 2026-04-08 reviewed
    AI search visibility requires repeated measurements

    Don't Measure Once: Measuring Visibility in AI Search (GEO)

    Julius Schulte +2

  14. cs.IR 2026-04-08 reviewed
    Hybrids improve both accuracy and diversity in recommendations

    HiMARS: Hybrid multi-objective algorithms for recommender systems

    Elaheh Lotfian +1

  15. cs.IR 2026-04-08 reviewed
    Benchmark tests AI on comparing music across track pairs

    Jamendo-MT-QA: A Benchmark for Multi-Track Comparative Music Question Answering

    Junyoung Koh +7

  16. cs.IR 2026-04-08 reviewed
    LLM framework lifts multimodal retrieval to 41.7 nDCG@10

    HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval

    Mahmoud Abdalla +5

  17. cs.IR 2026-04-08 reviewed
    RL query alignment outperforms multimodal encoders on text retrieval

    BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment

    Mohamed Darwish Mounis +6

  18. cs.IR 2026-04-08 reviewed
    Rerank system lifts watch time and slashes latency

    Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking

    Chao Zhang +7

  19. cs.IR 2026-04-08 reviewed
    VLM region descriptions align query rankings to lift document retrieval

    ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment

    Hao Yang +8

  20. cs.IR 2026-04-08 reviewed
    Artist catalogs double recall for new track recommendations

    Leveraging Artist Catalogs for Cold-Start Music Recommendation

    Yan-Martin Tamm +6

  21. cs.IR 2026-04-08 reviewed
    Reasoning pipeline lifts multimodal retrieval to 37.9 nDCG@10

    MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL

    Mahmoud SalahEldin Kasem +5

  22. cs.IR 2026-04-08 reviewed
    Intrinsic rewards strengthen LLM reasoning traces on complex queries

    SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval

    Roxana Petcu +2

  23. cs.DB 2026-04-08 reviewed
    Agent views help AI write complex SQL queries

    AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views

    Minh Tam Pham +5

  24. cs.IR 2026-04-08 reviewed
    Persona signals from knowledge graphs boost session recommendations

    Leveraging LLMs and Heterogeneous Knowledge Graphs for Persona-Driven Session-Based Recommendation

    Muskan Gupta +2

  25. cs.IR 2026-04-08 reviewed
    Calendar-time signals lift repurchase recommendation precision 8.6%

    CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation

    Yanan Cao +5

  26. cs.LG 2026-04-08 reviewed
    Event memory retrieval produces physics-consistent actions

    Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making

    Zhaowen Fan +1

  27. cs.AI 2026-04-08 reviewed
    Test checks if AI keeps facts straight across 250 stories

    ATANT: An Evaluation Framework for AI Continuity

    Samuel Sameer Tanguturi

  28. cs.DB 2026-04-08 reviewed
    CubeGraph stitches per-cell vector graphs for fast hybrid spatial search

    CubeGraph: Efficient Retrieval-Augmented Generation for Spatial and Temporal Data

    Mingyu Yang +2

  29. cs.CL 2026-04-08 reviewed
    LLM parser lifts missing-person data extraction F1 to 0.87 from 0.26

    LLM-based Schema-Guided Extraction and Validation of Missing-Person Intelligence from Heterogeneous Data Sources

    Joshua Castillo +1

  30. cs.IR 2026-04-07 reviewed
    More data keeps improving recommender performance without saturation

    The Unreasonable Effectiveness of Data for Recommender Systems

    Youssef Abdou

  31. cs.IR 2026-04-07 reviewed
    Retriever bias for LLM texts traces to training data

    Data, Not Model: Explaining Bias toward LLM Texts in Neural Retrievers

    Wei Huang +5

  32. cs.IR 2026-04-07 reviewed
    Benchmark unifies evaluation across Brazilian legal collections

    JU\'A -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections

    Jayr Pereira +4

  33. cs.IR 2026-04-07 reviewed
    LLM rewriting cuts RAG retriever bias by 54 percent

    Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG

    Agam Goyal +5

  34. cs.CL 2026-04-07 reviewed
    Multi-stage checks make LLM clinical extraction reliable at scale

    A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models

    Maria Mahbub +11

  35. cs.IR 2026-04-07 reviewed
    LLM profiles beat paper history for reviewer matching

    Beyond Paper-to-Paper: Structured Profiling and Rubric Scoring for Paper-Reviewer Matching

    Yicheng Pan +3

  36. cs.CL 2026-04-07 reviewed
    English bridges via reverse training boost cross-lingual retrieval up to 15%

    CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training

    Seungyoon Lee +5

  37. cs.CV 2026-04-07 reviewed
    WikiSeeker reassigns VLMs to refine queries and inspect retrieval

    WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering

    Yingjian Zhu +5

  38. cs.IR 2026-04-07 reviewed
    LLM retrieval systems post 20% gains on old benchmarks

    The LLM Effect on IR Benchmarks: A Meta-Analysis of Effectiveness, Baselines, and Contamination

    Moritz Staudinger +2

  39. cs.IR 2026-04-07 reviewed
    Generative retrieval beats dense methods on LIMIT but drops with ambiguous IDs

    Generative Retrieval Overcomes Limitations of Dense Retrieval but Struggles with Identifier Ambiguity

    Adrian Bracher +1

  40. cs.LG 2026-04-07 reviewed
    Topology extraction refines graphs for better heterogeneous learning

    Graph Topology Information Enhanced Heterogeneous Graph Representation Learning

    He Zhao +3

  41. cs.SE 2026-04-07 reviewed
    Siamese model detects semantic drift in links at 96% recall

    SemLink: A Semantic-Aware Automated Test Oracle for Hyperlink Verification using Siamese Sentence-BERT

    Guan-Yan Yang +4

  42. cs.IR 2026-04-07 reviewed
    2.8k samples correct English bias in multilingual retrieval

    Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment

    Seongtae Hong +4

  43. cs.AI 2026-04-07 reviewed
    Graph mined from agent trajectories improves tool sequencing

    SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation

    Hao Liu +1

  44. cs.IR 2026-04-07 reviewed
    Retrieval disagreement adapts person search models without labels

    Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search

    Jiahao Zhang +3

  45. cs.IR 2026-04-07 reviewed
    Perturbing single evidence items exposes hidden RAG utility patterns

    CUE-R: Beyond the Final Answer in Retrieval-Augmented Generation

    Siddharth Jain +1

  46. cs.IR 2026-04-07 reviewed
    Periodic updates plus augmentation improve LLM function calling

    Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA

    Xing Tang +9

  47. cs.IR 2026-04-07 reviewed
    ReAd refines sequential predictions using retrieved collaborative items

    Retrieve-then-Adapt: Retrieval-Augmented Test-Time Adaptation for Sequential Recommendation

    Xing Tang +8

  48. cs.IR 2026-04-07 reviewed
    LLMs build pseudo overlaps so diffusion can transfer preferences across domains

    From Clues to Generation: Language-Guided Conditional Diffusion for Cross-Domain Recommendation

    Ziang Lu +3

  49. cs.IR 2026-04-07 reviewed
    Curriculum RL aligns recommendation explanations with ratings

    Curr-RLCER:Curriculum Reinforcement Learning For Coherence Explainable Recommendation

    Xiangchen Pan +1

  50. cs.GT 2026-04-07 reviewed
    VCG payments plus multi-fidelity optimization maximize welfare in LLM ads

    Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models

    Jiayuan Liu +6