Skip to content

@DataScienceUIBK Data Science Group at Univ. of Innsbruck

Change the repository type filter

All

    Repositories list

    14 repositories

    • Rankify

      Public
      🔥 Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation 🔥. Our toolkit integrates 40 pre-retrieved benchmark datasets and supports 7+ retrieval techniques, 24+ state-of-the-art Reranking models, and multiple RAG methods.
      nlpagentinformation-retrievalairetrievalquestion-answeringrerankingragranked-retrievalllm
      Python
      •36•499•1•0•Updated Aug 23, 2025Aug 23, 2025

    • DeAR-Reranking

      Public
      DeAR (Deep Agent Rank) is a novel dual-stage document reranking framework that decouples fine-grained relevance scoring from holistic cross-document analysis. By combining knowledge distillation with reasoning agents, DeAR achieves superior accuracy and interpretability compared to single-stage approaches.
      0•1•0•0•Updated Aug 23, 2025Aug 23, 2025

    • llm-reranking-generalization-study

      Public
      How Good are LLM-based Rerankers? Accepted at EMNLP Findings 2025
      retrievalleaderboarddatasetrerankingrerankerllm
      Apache License 2.0
      •0•1•0•0•Updated Aug 22, 2025Aug 22, 2025

    • HintEval

      Public
      HintEval💡: A Comprehensive Framework for Hint Generation and Evaluation for Questions
      nlpeducationqanatural-language-processinginformation-retrievalframeworkpython-librarypython-libevaluationquestion-answering
      Python
      •
      Apache License 2.0
      •3•33•0•0•Updated Aug 21, 2025Aug 21, 2025

    • MultiOCR-QA

      Public
      MultiOCR-QA: Dataset for Evaluating Robustness of LLMs in Question Answering on Multilingual OCR Texts
      Python
      •
      MIT License
      •0•4•0•0•Updated Aug 20, 2025Aug 20, 2025

    • ChroniclingAmericaQA

      Public
      ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper Pages
      Python
      •
      MIT License
      •1•10•0•0•Updated Aug 19, 2025Aug 19, 2025

    • PlausibleQA

      Public
      Wrong Answers Can Also Be Useful: PlausibleQA — A QA Dataset with Answer Plausibility Scores
      MIT License
      •2•7•0•0•Updated Jul 27, 2025Jul 27, 2025

    • WikiHint

      Public
      WikiHint: A Human-Annotated Dataset for Hint Ranking and Generation
      Python
      •
      MIT License
      •1•2•0•0•Updated Jul 27, 2025Jul 27, 2025

    • TriviaHG

      Public
      A Dataset for Automatic Hint Generation from Factoid Questions
      Python
      •
      MIT License
      •2•26•0•0•Updated Jul 27, 2025Jul 27, 2025

    • SustainableQA

      Public
      SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reporting
      Python
      •
      Other
      •2•33•0•0•Updated Jul 1, 2025Jul 1, 2025

    • ComplexTempQA

      Public
      Python
      •
      Creative Commons Zero v1.0 Universal
      •2•6•3•0•Updated Jun 29, 2025Jun 29, 2025

    • HintQA

      Public
      Exploring Hint Generation Approaches in Open-Domain Question Answering
      Jupyter Notebook
      •
      MIT License
      •2•29•0•0•Updated Feb 20, 2025Feb 20, 2025

    • TempAmbiQA

      Public
      Detecting Temporal Ambiguity in Questions
      MIT License
      •0•2•0•0•Updated Nov 26, 2024Nov 26, 2024

    • ArabicaQA

      Public
      ArabicaQA: Comprehensive Dataset for Arabic Question Answering accepted at SIGIR 2024
      Python
      •
      MIT License
      •4•17•0•0•Updated Jul 28, 2024Jul 28, 2024