pith. sign in

archive

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

1286 papers in cs.IR · page 16

  1. cs.IR 2026-04-02 reviewed
    Two-phase retrieval and LLM-guided evolution raise job match quality

    Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization

    Ansel Kaplan Erol +3

  2. cs.DL 2026-04-02 reviewed
    Scholarly recommenders must track volatile contexts and research strands

    What Do Humanities Scholars Need? A User Model for Recommendation in Digital Archives

    Florian Atzenhofer-Baumgartner +1

  3. cs.IR 2026-04-02 reviewed
    Recommenders should stop pushing novelty at user-specific points

    Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty

    Enock O. Ayiku +2

  4. cs.IR 2026-04-02 reviewed
    Type routing lifts small models past large retrievers on chat memory

    SelRoute: Query-Type-Aware Routing for Long-Term Conversational Memory Retrieval

    Matthew McKee

  5. cs.IR 2026-04-02 reviewed
    Retrieval partially offsets smaller models on science tasks

    Do We Need Bigger Models for Science? Task-Aware Retrieval with Small Language Models

    Florian Kelber +3

  6. cs.IR 2026-04-02 reviewed
    Literature graphs project from tensor manifolds

    Tensor Manifold-Based Graph-Vector Fusion for AI-Native Academic Literature Retrieval

    Xing Wei +1

  7. cs.DB 2026-04-02 reviewed
    LLM tool adds database functions 34 percent more accurately

    Automating Database-Native Function Code Synthesis with LLMs

    Wei Zhou +6

  8. cs.IR 2026-04-01 reviewed
    Binary encoding matches alphanumeric codes without training

    Improving Search Suggestions for Alphanumeric Queries

    Samarth Agrawal +4

  9. cs.AI 2026-04-01 reviewed
    DeepSlide matches slide visuals but lifts narrative flow and pacing

    DeepSlide: From Artifacts to Presentation Delivery

    Ming Yang +5

  10. cs.CV 2026-04-01 reviewed
    ViT design choices aid active learning for cluttered object retrieval

    Revisiting Human-in-the-Loop Object Retrieval with Pre-Trained Vision Transformers

    Kawtar Zaher +2

  11. cs.CL 2026-04-01 reviewed
    Portuguese math benchmark shows LLM drops on figures and open answers

    MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese

    Tiago Teixeira +7

  12. cs.CL 2026-04-01 reviewed
    RAG assistant gives reliable answers on bachelor project rules

    Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projects

    Dumitru Ver\c{s}ebeniuc +6

  13. cs.IR 2026-04-01 reviewed
    Synthetic dictionary retrieves matches for 54% of unseen oracle bone characters

    Decoding Ancient Oracle Bone Script via Generative Dictionary Retrieval

    Yin Wu +6

  14. cs.CL 2026-04-01 reviewed
    TF-IDF arises from test statistic for word burstiness

    Common TF-IDF variants arise as key components in the test statistic of a penalized likelihood-ratio test for word burstiness

    Zeyad Ahmed +3

  15. cs.IR 2026-04-01 reviewed
    Agentic search narrows dense RAG's gap to GraphRAG

    Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems

    Dongzhe Fan +3

  16. cs.DB 2026-03-31 reviewed
    GPU bucketing delivers 240x faster hybrid searches

    GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing

    Xinkui Zhao +5

  17. cs.IR 2026-03-31 reviewed
    Router cuts large LLM use by nearly 30% in GraphRAG QA

    GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning

    Dongzhe Fan +4

  18. cs.CL 2026-03-31 reviewed
    Memory system reuses agent plans across unrelated tasks

    APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay

    Pratyay Banerjee +2

  19. cs.IR 2026-03-30 reviewed
    Percentile calibration lifts last-hop retrieval on multi-hop QA

    Calibrated Fusion for Heterogeneous Graph-Vector Retrieval in Multi-Hop QA

    Andre Bacellar

  20. cs.IR 2026-03-30 reviewed
    Agent trajectories train retrievers that raise recall and task success

    Learning to Retrieve from Agent Trajectories

    Yuqi Zhou +5

  21. cs.CV 2026-03-30 reviewed
    One LoRA toggles a model between retrieval and generation

    Hydra: Unifying Document Retrieval and Generation in a Single Vision-Language Model

    Athos Georgiou

  22. cs.IR 2026-03-30 reviewed
    Data prep beats PDF tool choice in RAG accuracy

    From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering

    Jos\'e Guilherme Marques dos Santos +10

  23. cs.IR 2026-03-30 reviewed
    SUMMIR ranks sports insights from LLMs while catching hallucinations

    SUMMIR: A Hallucination-Aware Framework for Ranking Sports Insights from LLMs

    Nitish Kumar +5

  24. cs.DL 2026-03-30 reviewed
    Vision-language models boost Italian parliament speech transcripts

    Transcription and Recognition of Italian Parliamentary Speeches Using Vision-Language Models

    Luigi Curini +3

  25. cs.AI 2026-03-29 reviewed
    Concept-mediated graph lifts agent memory retrieval

    GAAMA: Graph Augmented Associative Memory for Agents

    Swarna Kamal Paul +2

  26. cs.LG 2026-03-29 reviewed
    PLT cache beats frequency cache on expected inference cost

    Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse

    Gregory Magarshak

  27. cs.IR 2026-03-28 reviewed
    LLM agent fuses lexical and embedding search to match queries to dataset metadata

    A Reference Architecture for Agentic Hybrid Retrieval in Dataset Search

    Riccardo Terrenzi +3

  28. cs.HC 2026-03-28 reviewed
    LLM app gives instant ASD conversation feedback

    SocialWise: LLM-Agentic Conversation Therapy for Individuals with Autism Spectrum Disorder to Enhance Communication Skills

    Albert Tang

  29. cs.CL 2026-03-28 reviewed
    Metadata at file start routes LLM queries at 100% accuracy

    Self-Describing Structured Data with Dual-Layer Guidance: A Lightweight Alternative to RAG for Precision Retrieval in Large-Scale LLM Knowledge Navigation

    Hung Ming Liu

  30. cs.IR 2026-03-27 reviewed
    LLMs identify top articles with over 80% accuracy

    Large language models for post-publication research evaluation: Evidence from expert recommendations and citation indicators

    Mengjia Wu +3

  31. cs.IR 2026-03-27 reviewed
    Length bias holds for causal late interaction models

    Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models

    Antoine Edy +2

  32. cs.CL 2026-03-27 reviewed
    Memory pipeline gives AI agents cross-session recall

    Cognis: Context-Aware Memory for Conversational AI Agents

    Parshva Daftari +4

  33. cs.IR 2026-03-27 reviewed
    Static pipelines become self-evolving agent systems

    Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems

    Jinxin Hu +6

  34. cs.IR 2026-03-27 reviewed
    Agents automate recommender model reproduction from papers

    AgenticRS-Architecture: System Design for Agentic Recommender Systems

    Hao Zhang +6

  35. q-bio.NC 2026-03-27 reviewed
    Power-law forgetting emerges from interference in embeddings

    The Geometry of Forgetting

    Sambartha Ray Barman +4

  36. cs.CY 2026-03-27 reviewed
    AI oncology planner earns high clinician ratings on accuracy and safety

    Clinical Reasoning AI for Oncology Treatment Planning: A Multi-Specialty Case-Based Evaluation

    Philippe E. Spiess +35

  37. cs.CV 2026-03-26 reviewed
    Metric spots incoherent multimodal inputs better than accuracy

    Good Scores, Bad Data: A Metric for Multimodal Coherence

    Vasundra Srinivasan

  38. cs.CL 2026-03-26 reviewed
    Hybrid retrieval resolves RAG trade-off in financial queries

    Resolving the Robustness-Precision Trade-off in Financial RAG through Hybrid Document-Routed Retrieval

    Zhiyuan Cheng +2

  39. cs.CV 2026-03-25 reviewed
    Positive-first criterion boosts rare visual category retrieval

    Positive-First Most Ambiguous: A Simple Active Learning Criterion for Interactive Retrieval of Rare Categories

    Kawtar Zaher +2

  40. cs.IR 2026-03-25 reviewed
    Generative search lifts CTR 4 percent by internalizing latent user reasoning

    OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework

    Ben Chen +22

  41. cs.CV 2026-03-25 reviewed
    Lightweight filter cuts vision tokens for document parsing

    Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing

    Cheng Cui +17

  42. cs.IR 2026-03-25 reviewed
    Joint data-model scaling lifts e-commerce purchases 1.7%

    Joint Model Parameter Scaling and Universal-Domain Data Integration for E-commerce Search Ranking

    Liren Yu +7

  43. cs.IR 2026-03-25 reviewed
    LLM motives enable accurate recs in sparse industrial data

    LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains

    Ryogo Hishikawa +2

  44. cs.CY 2026-03-23 reviewed
    LLM moral advice responses reinforce human-like assumptions

    Implicit Humanization in Everyday LLM Moral Judgments

    Hoda Ayad +1

  45. cs.CL 2026-03-22 reviewed
    Semantic shift, not length, drives embedding collapse

    Pooling and Semantic Shift: The Fundamental Challenges in Long Text Embedding and Retrieval

    Hang Gao +3

  46. cs.IR 2026-03-20 reviewed
    Item-aware attention lets LLMs capture item-level collaborations

    Beyong Tokens: Item-aware Attention for LLM-based Recommendation

    Xiaokun Zhang +4

  47. cs.IR 2026-03-19 reviewed
    Adaptive gamma from spectrum achieves near-optimal embedding compression

    Spectral Tempering for Embedding Compression in Dense Passage Retrieval

    Yongkang Li +2

  48. cs.IR 2026-03-18 reviewed
    Pairwise comparisons boost LLM paper ranking by 21.8% over baselines

    From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation

    Pujun Zheng +8

  49. cs.IR 2026-03-18 reviewed
    Lightweight profiler sets new record in citation recommendations

    Public Profile Matters: A Scalable Integrated Approach to Recommend Citations in the Wild

    Karan Goyal +3

  50. cs.IR 2026-03-17 reviewed
    Modular stages let small models answer farm questions accurately

    AgriIR: A Scalable Framework for Domain-Specific Knowledge Retrieval

    Shuvam Banerji Seal +3