Skip to content

All

    Repositories list

    • RETECO

      Public
      RETECO: A SemEval-2027 Shared Task on Reasoning-Oriented Retrieval
      Python
      0100Updated Aug 30, 2026Aug 30, 2026
    • HintEval

      Public
      HintEval 💡: An Open-Source Python Toolkit for Hint Generation and Hint Evaluation
      Python
      Apache License 2.0
      33700Updated Aug 29, 2026Aug 29, 2026
    • SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reporting
      Python
      Other
      24510Updated Aug 26, 2026Aug 26, 2026
    • PopMCQ

      Public
      Large Language Models Systematically Favor Popular Options: Evidence and Mitigation Across MCQs
      Python
      Other
      0100Updated Aug 24, 2026Aug 24, 2026
    • SmallReason-ColBERT: An Ultra-Small Late-Interaction Retriever for Reasoning Intensive Retrieval
      Python
      Apache License 2.0
      0100Updated Aug 23, 2026Aug 23, 2026
    • REGREACT

      Public
      REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction
      0000Updated Aug 23, 2026Aug 23, 2026
    • obliq-ir

      Public
      OBLIQ-IR: Training a Dense Retriever for Oblique Queries
      Python
      MIT License
      0500Updated Aug 23, 2026Aug 23, 2026
    • Python
      Apache License 2.0
      0100Updated Aug 13, 2026Aug 13, 2026
    • Python
      0100Updated Aug 13, 2026Aug 13, 2026
    • This repository contains materials, code, and resources for the SIGIR 2026 tutorial on temporal information retrieval and extraction, covering foundational conc…
      HTML
      0000Updated Aug 10, 2026Aug 10, 2026
    • Code and experiments for studying convergence-based passage construction in inferential QA, demonstrating improvements over cosine similarity in retrieval-augme…
      Python
      MIT License
      1100Updated Jul 15, 2026Jul 15, 2026
    • Official repository for studying how pretraining exposure drives popularity bias in large language models.
      Python
      MIT License
      1100Updated Jul 15, 2026Jul 15, 2026
    • Tutorial website for "Temporal Information Retrieval and Question Answering in the Age of LLMs" at WWW 2026 Conference
      HTML
      0100Updated Jul 7, 2026Jul 7, 2026
    • RecencyQA

      Public
      How often do Answers Change? Estimating Recency Requirements in Question Answering
      Python
      MIT License
      0200Updated Jul 2, 2026Jul 2, 2026
    • Region-Aware Query-Conditioned Mixture-of-Experts for Visual Document Retrieval
      0600Updated Jun 7, 2026Jun 7, 2026
    • hlqa

      Public
      Collaborative Reasoning and Human-Centered QA in the GenAI Era
      HTML
      MIT License
      0000Updated Jun 1, 2026Jun 1, 2026
    • Rankify

      Public
      🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark dat…
      Python
      7168226Updated May 6, 2026May 6, 2026
    • Survey of datasets, methods, and tools for Temporal Question Answering.
      0600Updated Apr 17, 2026Apr 17, 2026
    • HTML
      0000Updated Apr 13, 2026Apr 13, 2026
    • Q-DAPS

      Public
      Estimate question difficulty for LLMs via answer plausibility scoring and entropy-based uncertainty.
      MIT License
      0000Updated Apr 9, 2026Apr 9, 2026
    • Official repository for "Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overhead", accepted at SIGIR 202…
      0100Updated Apr 4, 2026Apr 4, 2026
    • Parse

      Public
      An Open-Domain Reasoning Question Answering Benchmark for Persian
      HTML
      MIT License
      1300Updated Feb 7, 2026Feb 7, 2026
    • tempoeval

      Public
      Python
      MIT License
      1300Updated Feb 5, 2026Feb 5, 2026
    • TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions Accepted at WSDM main 2026
      0100Updated Dec 1, 2025Dec 1, 2025
    • RankArena

      Public
      RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback — CIKM ’25, Seoul, Nov 10–14, 2025.
      Python
      Apache License 2.0
      1400Updated Nov 26, 2025Nov 26, 2025
    • Python
      Creative Commons Zero v1.0 Universal
      21230Updated Nov 11, 2025Nov 11, 2025
    • DeAR (Deep Agent Rank): Dual-Stage Document Reranking with Reasoning Agents Accepted at EMNLP Findings 2025
      Python
      0810Updated Oct 23, 2025Oct 23, 2025
    • HintQA

      Public
      Exploring Hint Generation Approaches in Open-Domain Question Answering
      Jupyter Notebook
      MIT License
      23100Updated Sep 19, 2025Sep 19, 2025
    • How Good are LLM-based Rerankers? Accepted at EMNLP Findings 2025
      Apache License 2.0
      01200Updated Aug 28, 2025Aug 28, 2025
    • Evaluating Robustness of LLMs in Question Answering on Multilingual NOisy OCR Data
      Python
      MIT License
      0600Updated Aug 20, 2025Aug 20, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.