pith. sign in

archive

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

1286 papers in cs.IR · page 5

  1. cs.IR 2026-05-08 reviewed
    Hyperlinks as metadata improve RAG quality and efficiency

    LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentation

    Giorgia Bolognesi +5

  2. cs.CV 2026-05-08 reviewed
    Multimodal agents score below 50% on interleaved search benchmark

    InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search

    Bohan Hou +7

  3. cs.CL 2026-05-08 reviewed
    Browser LLM tool extracts structured data from papers at 94% compliance

    TCMIIES: A Browser-Based LLM-Powered Intelligent Information Extraction System for Academic Literature

    Hanqing Zhao

  4. cs.IR 2026-05-08 reviewed
    Skills enable reliable, reusable execution in LLM agents

    A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

    Yingli Zhou +5

  5. cs.IR 2026-05-08 reviewed
    Skills as reusable procedures scale LLM agents

    A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

    Yingli Zhou +5

  6. cs.IR 2026-05-08 reviewed
    Dual channels separate semantics from behavior to lift sparse recommendations

    DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation

    Xinchi Zou +6

  7. cs.IR 2026-05-08 reviewed
    PRISM models interacting preference and relevance in e-commerce search

    PRISM: Refracting the Entangled User Behavior Space for E-Commerce Search

    Haoqian Zhang +2

  8. cs.IR 2026-05-08 reviewed
    Multilingual retrievers split between semantic strength and language match

    MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal

    Youngjoon Jang +3

  9. cs.IR 2026-05-08 reviewed
    LARGER raises coding agent file retrieval accuracy by 11-13 points

    LARGER: Lexically Anchored Repository Graph Exploration and Retrieval

    Yuntong Hu +4

  10. cs.IR 2026-05-08 reviewed
    Parallel tokens in diffusion LMs top BEIR-7 retrieval scores

    DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models

    Shuai Wang +4

  11. cs.IR 2026-05-08 reviewed
    Embeddings match sub-fields but miss agendas 80 percent of the time

    Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings

    Junseon Yoo

  12. cs.IR 2026-05-08 reviewed
    LLMs learn to fetch memories dynamically for better recommendations

    RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation

    Shijun Li +4

  13. cs.IR 2026-05-08 reviewed
    Simple graph heuristic beats trained recommenders on benchmarks

    An Embarrassingly Simple Graph Heuristic Reveals Shortcut-Solvable Benchmarks for Sequential Recommendation

    Haoyu Han +11

  14. cs.IR 2026-05-08 reviewed
    RL picks per-request utility weights for Pinterest Homefeed

    A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems

    Yichu Zhou +11

  15. cs.IR 2026-05-07 reviewed
    RL aligns LLM text profiles with embeddings for recommendations

    Bridging Textual Profiles and Latent User Embeddings for Personalization

    Zhaoxuan Tan +4

  16. cs.HC 2026-05-07 reviewed
    Moodle AI tutor grounded in teacher content reaches 0.97 faithfulness

    From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle

    Anna Ostrowska +6

  17. cs.IR 2026-05-07 reviewed
    Single lexical query outperforms multi-round retrieval agents

    Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval

    Zeyu Yang +3

  18. cs.IR 2026-05-07 reviewed
    Pruning trims deep recommenders while raising accuracy

    Light-FMP: Lightweight Feature and Model Pruning for Enhanced Deep Recommender Systems

    Nghia Bui +2

  19. cs.CL 2026-05-07 reviewed
    Convergence nodes annotate cells from gene sets with one LLM call

    GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation

    Zhonghui Zhang +4

  20. cs.IR 2026-05-07 reviewed
    Semantic ID trees block simple preferences in generative recommenders

    Expressiveness Limits of Autoregressive Semantic ID Generation in Generative Recommendation

    Yupeng Hou +5

  21. cs.AI 2026-05-07 reviewed
    LLM pipeline annotates PII in HTTP traffic for any taxonomy

    Addressing Labelled Data Scarcity: Taxonomy-Agnostic Annotation of PII Values in HTTP Traffic using LLMs

    Thomas Cory +1

  22. cs.IR 2026-05-07 reviewed
    Retrievers miss most documents that match latent patterns

    OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries

    Diane Tchuindjo +2

  23. cs.CV 2026-05-07 reviewed
    The paper introduces Holmes, a hierarchical evidential learning method for retrieving…

    Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval

    Jun Li +7

  24. cs.IR 2026-05-07 reviewed
    Agents automate e-commerce search relevance fixes

    A Case-Driven Multi-Agent Framework for E-Commerce Search Relevance

    Global E-Commerce Search Relevance Team

  25. cs.IR 2026-05-07 reviewed
    Active queries lift conversation starter penetration by 0.54%

    Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling

    Yiqing Wu +6

  26. cs.IR 2026-05-07 reviewed
    Value signals folded into generative ad tokens raise hit rate 37%

    Unified Value Alignment for Generative Recommendation in Industrial Advertising

    Xinxun Zhang +15

  27. cs.IR 2026-05-07 reviewed
    Rebuilding rare location transitions lifts next-POI accuracy

    Beyond Long Tail POIs: Transition-Centered Generalization for Human Mobility Prediction

    Dingyang Lyu +3

  28. cs.IR 2026-05-07 reviewed
    Router and transmitter modules transfer knowledge to lift CVR prediction

    Effective Knowledge Transfer for Multi-Task Recommendation Models

    Guohao Cai +2

  29. cs.AI 2026-05-07 reviewed
    Bidirectional channels close RAG's text-graph gaps

    Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG

    Jiarui Zhong +1

  30. cs.AI 2026-05-07 reviewed
    Agentic tools lift enterprise retrieval recall by 22 points

    AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases

    Susheel Suresh +4

  31. cs.CV 2026-05-06 reviewed
    LLM adds context to lift satellite query retrieval by 16 percent

    Open-SAT: LLM-Guided Query Embedding Refinement for Open-Vocabulary Object Retrieval in Satellite Imagery

    Md Adnan Arefeen +4

  32. cs.CR 2026-05-06 reviewed
    Policy gating blocks cross-tenant leaks in shared AI retrieval

    Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use

    Francisco Javier Arceo +1

  33. cs.IR 2026-05-06 reviewed
    Burn-down diffusion models interest decay for better CF recommendations

    Interests Burn-down Diffusion Process for Personalized Collaborative Filtering

    Yifang Qin +5

  34. cs.IR 2026-05-06 reviewed
    Capsule routing yields better semantic IDs for recommendation

    CapsID: Soft-Routed Variable-Length Semantic IDs for Generative Recommendation

    Wenzhuo Cheng +6

  35. cs.SD 2026-05-06 reviewed
    2.5K pop samples restore accuracy in jazz-tuned chord model

    Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation

    Jinju Lee

  36. cs.CV 2026-05-06 reviewed
    Modular pipeline with origin tracking turns table images into traceable KGs

    From Historical Tabular Image to Knowledge Graphs: A Provenance-Aware Modular Pipeline

    Sarah Binta Alam Shoilee +3

  37. cs.CL 2026-05-06 reviewed
    TabEmbed outperforms text models on tabular tasks

    TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding

    Minjie Qiang +7

  38. cs.IR 2026-05-06 reviewed
    Enriched SERP dataset labels every element with boxes and types

    AllSERP: Exhaustive Per-Element Enrichment of the Versatile AdSERP Dataset

    K. Andrew Edmonds

  39. cs.IR 2026-05-06 reviewed
    AllSERP adds per-element boxes and types to AdSERP corpus

    AllSERP: Exhaustive Per-Element Enrichment of the Versatile AdSERP Dataset

    K. Andrew Edmonds

  40. cs.CL 2026-05-06 reviewed
    Verbatim events and staged retrieval replace extraction for agent memory

    Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall

    Joshua Adler +1

  41. cs.LG 2026-05-06 reviewed
    Longer contexts worsen time series forecasts

    Retrieval Mechanisms Surpass Long-Context Scaling in Time Series Forecasting

    Rishi Ahuja +3

  42. cs.IR 2026-05-06 reviewed
    Crowd aggregation stabilizes deepfake authenticity but not type ID

    Beyond Seeing Is Believing: On Crowdsourced Detection of Audiovisual Deepfakes

    Michael Soprano +2

  43. cs.IR 2026-05-06 reviewed
    On-device LLM lifts Taobao recommendation accuracy

    RecGPT-Mobile: On-Device Large Language Models for User Intent Understanding in Taobao Feed Recommendation

    Bin Zhang +11

  44. cs.IR 2026-05-06 reviewed
    Hierarchical convolutions outperform attention on user sequences

    Rethinking Convolutional Networks for Attribute-Aware Sequential Recommendation

    Shereen Elsayed +3

  45. cs.IR 2026-05-06 reviewed
    Bayesian updates break static bound for LLM recommendation alignment

    Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation

    Ruijun Chen +4

  46. cs.IR 2026-05-06 reviewed
    Career vault lifts ATS scores 7.8 points for matching roles

    Career-Aware Resume Tailoring via Multi-Source Retrieval-Augmented Generation with Provenance Tracking: A Case Study

    Kumar Abhinav

  47. cs.CL 2026-05-06 reviewed
    Three-stage pipeline automates QA nuggets for report evaluation

    DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation

    Bryan Li +8

  48. cs.DC 2026-05-06 reviewed
    Adaptive HBM split cuts recommender P99 latency 24-38%

    One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving

    Wenjun Yu +2

  49. cs.IR 2026-05-05 reviewed
    New benchmark tests RAG on 500,000 enterprise documents

    EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge

    Yuhong Sun +6

  50. cs.IR 2026-05-05 reviewed
    New benchmark tests RAG on 500k company documents

    EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge

    Yuhong Sun +6