Skip to content
@IAAR-Shanghai

LLM Group, Institute for Advanced Algorithms Research, Shanghai

Popular repositories Loading

  1. SurveyX SurveyX Public

    Academic Survey Paper Generation.

    TeX 792 66

  2. Awesome-Attention-Heads Awesome-Attention-Heads Public

    An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

    TeX 332 10

  3. CRUD_RAG CRUD_RAG Public

    CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

    Python 291 23

  4. ICSFSurvey ICSFSurvey Public

    Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

    Jupyter Notebook 164 4

  5. CTGSurvey CTGSurvey Public

    Controllable Text Generation for Large Language Models: A Survey

    TeX 164 9

  6. UHGEval UHGEval Public

    [ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.

    Python 161 17

Repositories

Showing 10 of 19 repositories
  • xVerify Public

    xVerify: Efficient Answer Verifier for Large Language Model Evaluations

    IAAR-Shanghai/xVerify’s past year of commit activity
    Python 17 1 0 0 Updated Mar 28, 2025
  • SurveyX Public

    Academic Survey Paper Generation.

    IAAR-Shanghai/SurveyX’s past year of commit activity
    TeX 792 66 14 0 Updated Mar 19, 2025
  • Meta-Chunking Public

    Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception

    IAAR-Shanghai/Meta-Chunking’s past year of commit activity
    Python 143 Apache-2.0 7 0 0 Updated Mar 15, 2025
  • SEAP Public
    IAAR-Shanghai/SEAP’s past year of commit activity
    Jupyter Notebook 19 0 0 0 Updated Mar 14, 2025
  • SafeRAG Public
    IAAR-Shanghai/SafeRAG’s past year of commit activity
    Python 24 2 0 0 Updated Mar 11, 2025
  • Awesome-Attention-Heads Public

    An awesome repository & A comprehensive survey on interpretability of LLM attention heads.

    IAAR-Shanghai/Awesome-Attention-Heads’s past year of commit activity
    TeX 332 10 4 0 Updated Mar 2, 2025
  • xFinder Public

    [ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation

    IAAR-Shanghai/xFinder’s past year of commit activity
    Python 159 7 2 0 Updated Feb 26, 2025
  • QAEncoder Public
    IAAR-Shanghai/QAEncoder’s past year of commit activity
    Python 93 8 1 0 Updated Jan 26, 2025
  • ICSFSurvey Public

    Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

    IAAR-Shanghai/ICSFSurvey’s past year of commit activity
    Jupyter Notebook 164 4 0 0 Updated Dec 7, 2024
  • UHGEval Public

    [ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.

    IAAR-Shanghai/UHGEval’s past year of commit activity
    Python 161 Apache-2.0 17 0 0 Updated Nov 12, 2024