pith. sign in

archive

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

1286 papers in cs.IR · page 15

  1. cs.IR 2026-04-07 reviewed
    Semantic trimming speeds generative rec training by 23-38%

    Semantic Trimming and Auxiliary Multi-step Prediction for Generative Recommendation

    Tianyu Zhan +4

  2. cs.IR 2026-04-07 reviewed
    Tree-based next-scale generator reranks lists scale by scale

    Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan

    Shuli Wang +7

  3. cs.IR 2026-04-07 reviewed
    Hidden sequence split inflates recent recommendation scores

    Pay Attention to Sequence Split: Uncovering the Impacts of Sub-Sequence Splitting on Sequential Recommendation Models

    Yizhou Dang +7

  4. cs.IR 2026-04-06 reviewed
    Immersive recommenders repeat visible info and miss next questions

    Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendation

    Jiazhou Liang +5

  5. cs.IR 2026-04-06 reviewed
    MaxSim pooling spikes gradients and hurts long-document retrieval

    Spike Hijacking in Late-Interaction Retrieval

    Karthik Suresh +4

  6. cs.IR 2026-04-06 reviewed
    DotRAG makes retrieval a reasoning process over paths

    DOTRAG: Retrieval-Time Reasoning Along Paths

    Larnell Moore +3

  7. cs.IR 2026-04-06 reviewed
    Entity signals add no MAP value in open-world retrieval

    Entities as Retrieval Signals: A Systematic Study of Coverage, Supervision, and Evaluation in Entity-Oriented Ranking

    Shubham Chatterjee

  8. cs.CL 2026-04-06 reviewed
    RAG-enhanced MedGemma scores 89% on EHR trial screening

    Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives

    Ziyi Chen +3

  9. cs.IR 2026-04-06 reviewed
    RL policies cut retrieval steps by 47% at 92% accuracy

    Offline RL for Adaptive Policy Retrieval in Prior Authorization

    Ruslan Sharifullin +2

  10. cs.IR 2026-04-06 reviewed
    Codebook rebalancing cuts popularity bias in generative recommenders

    CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation

    Zezhong Fan +7

  11. cs.CL 2026-04-06 reviewed
    RL optimizes documents to boost black-box retriever accuracy

    Document Optimization for Black-Box Retrieval via Reinforcement Learning

    Omri Uzan +3

  12. cs.CL 2026-04-06 reviewed
    Skill library from strong agents lifts weaker ones

    SkillX: Automatically Constructing Skill Knowledge Bases for Agents

    Chenxi Wang +10

  13. cs.IR 2026-04-06 reviewed
    DisastRAG lifts disaster query accuracy 12-23 points

    DisastRAG: A Multi-Source Disaster Information Integration and Access System Based on Retrieval-Augmented Large Language Models

    Bo Li +5

  14. cs.IR 2026-04-06 reviewed
    RAG system gains 12-23 points on disaster info tasks

    DisastRAG: A Multi-Source Disaster Information Integration and Access System Based on Retrieval-Augmented Large Language Models

    Bo Li +5

  15. cs.IR 2026-04-06 reviewed
    Stratified sampling beats hard negatives in retrieval distillation

    Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval

    Youngjoon Jang +3

  16. cs.IR 2026-04-06 reviewed
    Ruling out mimics boosts medical QA retrieval

    Ruling Out to Rule In: Contrastive Hypothesis Retrieval for Medical Question Answering

    Byeolhee Kim +3

  17. cs.IR 2026-04-06 reviewed
    Contrastive learning disentangles long- and short-term interests

    SLSREC: Self-Supervised Contrastive Learning for Adaptive Fusion of Long- and Short-Term User Interests

    Wei Zhou +7

  18. cs.AI 2026-04-06 reviewed
    Human-inspired forgetting lifts AI agent memory to 70% on benchmarks

    SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

    Varun Pratap Bhardwaj

  19. cs.IR 2026-04-06 reviewed
    RL aligns retrieval and generation stages in recommender systems

    Retrieval Augmented Conversational Recommendation with Reinforcement Learning

    Zhenrui Yue +6

  20. cs.IR 2026-04-06 reviewed
    One-step flow model delivers 10x faster sequential recommendations

    FAVE: Flow-based Average Velocity Establishment for Sequential Recommendation

    Ke Shi +6

  21. cs.CL 2026-04-05 reviewed
    Small models structure kidney biopsy reports on ordinary computers

    A Semi-Automated Annotation Workflow for Paediatric Histopathology Reports Using Small Language Models

    Avish Vijayaraghavan +13

  22. cs.IR 2026-04-05 reviewed
    Formalized topics raise LLM judgment agreement

    Formalized Information Needs Improve Large-Language-Model Relevance Judgments

    J\"uri Keller +6

  23. cs.IR 2026-04-05 reviewed
    Single network matches ensemble performance in sequential recs

    FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation

    WooJoo Kim +5

  24. cs.IR 2026-04-05 reviewed
    Dual-hypergraph RAG raises math teacher feedback quality by 15%

    MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers

    Zhihan Guo +3

  25. cs.IR 2026-04-04 reviewed
    Circuit edits enable effective unlearning in LLM recommenders

    CURE:Circuit-Aware Unlearning for LLM-based Recommendation

    Ziheng Chen +6

  26. cs.IR 2026-04-04 reviewed
    Two datasets give generative recommenders 10 million real ad users

    Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation

    Junwei Pan +22

  27. cs.IR 2026-04-04 reviewed
    Popularity outranks AI models in item-level explanation ranking

    Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation

    Ben Kabongo +2

  28. cs.IR 2026-04-04 reviewed
    LLM embeddings fused and aligned boost tail-item recommendations

    Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendation

    Zhifu Wei +4

  29. cs.CL 2026-04-04 reviewed
    LightThinker++ cuts LLM peak tokens by 70% while raising accuracy

    LightThinker++: From Reasoning Compression to Memory Management

    Yuqi Zhu +9

  30. cs.IR 2026-04-04 reviewed
    Specialized retrievers match top effectiveness with competitive throughput

    Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead

    Abdelrahman Abdallah +3

  31. cs.AI 2026-04-04 reviewed
    Co-training aligns process rewards in search agents

    OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search

    Erhan Zhang +8

  32. cs.IR 2026-04-04 reviewed
    RL with simulator guidance reduces bias in multi-turn recommendations

    User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation

    Xingyuan Xiang +2

  33. cs.IR 2026-04-04 reviewed
    Multimodal paths boost LLM explainable recommendations

    MMP-Refer: Multimodal Path Retrieval-augmented LLMs For Explainable Recommendation

    Xiangchen Pan +1

  34. cs.IR 2026-04-04 reviewed
    Conditional diffusion denoises multimodal recs and augments pairs

    Joint Behavior-guided and Modality-coherence Conditional Graph Diffusion Denoising for Multi Modal Recommendation

    Xiangchen Pan +1

  35. cs.IR 2026-04-04 reviewed
    MG²-RAG speeds multimodal graph construction 43 times with SOTA accuracy

    MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation

    Sijun Dai +3

  36. cs.AI 2026-04-03 reviewed
    TRACE-KG induces reusable schemas while building traceable graphs

    Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graphs from Complex Documents

    Mohammad Sadeq Abolhasani +3

  37. cs.IR 2026-04-03 reviewed
    TF-IDF SVM routes RAG queries at 93% accuracy

    Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench

    Prakhar Bansal +1

  38. cs.IR 2026-04-03 reviewed
    Two-stage adapter aligns query and document spaces for low-label retrieval

    Align then Train: Efficient Retrieval Adapter Learning

    Seiji Maekawa +3

  39. cs.IR 2026-04-03 reviewed
    Bridge conditioning lifts multi-hop retrieval without training

    BridgeRAG: Training-Free Bridge-Conditioned Retrieval for Multi-Hop Question Answering

    Andre Bacellar

  40. cs.LG 2026-04-03 reviewed
    Sparse LLM labels train sharper topic clusters than big models

    PRISM: LLM-Guided Semantic Clustering for High-Precision Topics

    Connor Douglas +2

  41. cs.IR 2026-04-03 reviewed
    User-specific diffusion filtering boosts multi-modal recommendation

    User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation

    Jing Du +4

  42. cs.IR 2026-04-03 reviewed
    Multi-agent systems self-optimize to match expert prompts

    Self-Optimizing Multi-Agent Systems for Deep Research

    Arthur C\^amara +2

  43. cs.IR 2026-04-03 reviewed
    Prompt compression cuts LLM inference time up to 18% when conditions match

    Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference

    Cornelius Kummer +3

  44. cs.IR 2026-04-03 reviewed
    BIPCL lifts sequential recs via bilateral intent prototypes and perturbations

    BIPCL: Bilateral Intent-Enhanced Sequential Recommendation via Embedding Perturbation Contrastive Learning

    Shanfan Zhang +2

  45. cs.CV 2026-04-03 reviewed
    AI now builds video trailers instead of selecting clips

    Generative AI for Video Trailer Synthesis: From Extractive Heuristics to Autoregressive Creativity

    Abhishek Dharmaratnakar +3

  46. cs.IR 2026-04-03 reviewed
    Auto-generated annotations replace embeddings for cheaper document search

    AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis

    Teng Lin +2

  47. cs.IR 2026-04-03 reviewed
    MBGR fixes seesaw effect in multi-business generative recs

    MBGR: Multi-Business Prediction for Generative Recommendation at Meituan

    Changhao Li +8

  48. cs.IR 2026-04-03 reviewed
    Agentic affordance reasoning improves context-sensitive POI ranking

    Agent4POI: Agentic Context-Conditioned Affordance Reasoning for Multimodal Point-of-Interest Recommendation

    Jinze Wang +7

  49. cs.AI 2026-04-03 reviewed
    LLM agents verify technical claims without experts

    AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models

    Yuntao Du +3

  50. cs.CL 2026-04-02 reviewed
    Quadratic program retrieves diverse RAG passages with speedup

    Principled and Scalable Diversity-Aware Retrieval via Cardinality-Constrained Binary Quadratic Programming

    Qiheng Lu +1