Skip to content

@THU-KEG THU-KEG

Change the repository type filter

All

    Repositories list

    83 repositories

    • VerIF

      Public
      [EMNLP 2025] Verification Engineering for RL in Instruction Following
      Python
      •
      Apache License 2.0
      •0•30•2•4•Updated Aug 4, 2025Aug 4, 2025

    • RM-Bench-Leaderboard

      Public
      0•1•1•0•Updated Jul 23, 2025Jul 23, 2025

    • RM-Bench

      Public
      [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
      Python
      •2•59•3•0•Updated Jul 18, 2025Jul 18, 2025

    • OpenSAE

      Public
      Python
      •
      MIT License
      •1•28•0•0•Updated Jul 17, 2025Jul 17, 2025

    • LRM-FactEval

      Public
      Python
      •2•11•1•0•Updated Jun 25, 2025Jun 25, 2025

    • StoryWriter

      Public
      Python
      •2•12•0•0•Updated Jun 18, 2025Jun 18, 2025

    • LLMAEL

      Public
      [ACL Workshop 2025] LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking
      Python
      •1•12•1•0•Updated Jun 16, 2025Jun 16, 2025

    • Agentic-Reward-Modeling

      Public
      [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
      Python
      •
      MIT License
      •5•102•0•0•Updated Jun 11, 2025Jun 11, 2025

    • AdaptThink

      Public
      Python
      •
      MIT License
      •12•146•2•0•Updated May 28, 2025May 28, 2025

    • AtomR

      Public
      [KDD 2025] AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning
      Jupyter Notebook
      •2•12•0•0•Updated May 27, 2025May 27, 2025

    • MMGeoLM

      Public
      Python
      •0•6•1•0•Updated May 27, 2025May 27, 2025

    • Crab

      Public
      Constraint Back-translation Improves Complex Instruction Following of Large Language Models
      Python
      •0•14•0•0•Updated May 23, 2025May 23, 2025

    • AgentIF

      Public
      AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
      Python
      •0•17•1•1•Updated May 23, 2025May 23, 2025

    • ReaRAG

      Public
      ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
      Python
      •2•18•0•0•Updated May 8, 2025May 8, 2025

    • PairJudgeRM

      Public
      Python
      •0•11•0•0•Updated Apr 14, 2025Apr 14, 2025

    • LongWriter-V

      Public
      [ACM MM25] LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models
      Python
      •
      MIT License
      •0•19•0•0•Updated Mar 29, 2025Mar 29, 2025

    • Linguistic-SAE

      Public
      Python
      •1•1•0•0•Updated Mar 20, 2025Mar 20, 2025

    • MRCEval

      Public
      MRCEval: A Comprehensive, Challenging and Accessible Machine Reading Comprehension Benchmark
      Python
      •
      MIT License
      •0•4•0•0•Updated Mar 12, 2025Mar 12, 2025

    • OmniEvent

      Public
      A comprehensive, unified and modular event extraction toolkit.
      natural-language-processingdeep-learningpytorchevent-detectionevent-extractionnatural-language-generationhuggingface-transformersinformation-extrationbig-modelsbmtrain
      Python
      •
      MIT License
      •37•388•8•4•Updated Dec 18, 2024Dec 18, 2024

    • ADELIE

      Public
      [EMNLP2024] Aligning Large Language Models on Information Extraction
      Python
      •2•53•1•0•Updated Nov 4, 2024Nov 4, 2024

    • KB-Plugin

      Public
      [EMNLP2024] KB-Plugin: A Plug-and-play Framework for Large Language Models to Induce Programs over Low-resourced Knowledge Bases
      Python
      •1•9•0•0•Updated Oct 16, 2024Oct 16, 2024

    • MOOC-Radar

      Public
      The data and source code for the paper "MoocRadar: A Fine-grained and Multi-aspect Knowledge Repository for Improving Cognitive Student Modeling in MOOCs"
      Python
      •2•46•6•0•Updated Oct 7, 2024Oct 7, 2024

    • DICE

      Public
      DICE: Detecting In-distribution Data Contamination with LLM's Internal State
      benchmarkdata-contaminationsftllmgsm8kfine-tuning-llm
      Python
      •
      MIT License
      •0•9•0•0•Updated Sep 21, 2024Sep 21, 2024

    • SafetyNeuron

      Public
      Data and code for the paper: Finding Safety Neurons in Large Language Models
      safetyllmsmechanistic-interpretability
      Jupyter Notebook
      •
      MIT License
      •0•7•2•0•Updated Sep 21, 2024Sep 21, 2024

    • LLM_Reasoning_Papers

      Public
      Papers on LLM Reasoning and Retrieval-Augmented LLM Reasoning
      0•7•0•0•Updated Aug 27, 2024Aug 27, 2024

    • DiaKoP

      Public
      DiaKoP (CIKM Demo 2024)
      dialogue-systemskbqa
      JavaScript
      •0•4•0•0•Updated Aug 7, 2024Aug 7, 2024

    • MAVEN-FACT

      Public
      Python
      •0•5•0•0•Updated Jul 22, 2024Jul 22, 2024

    • Knowledge-to-Jailbreak

      Public
      Data and Code for the paper, Knowledge-to-Jailbreak: One Knowledge Point Worth One Attack.
      Python
      •3•8•0•0•Updated Jun 28, 2024Jun 28, 2024

    • SeaKR

      Public
      Python
      •
      GNU General Public License v3.0
      •6•30•4•0•Updated Jun 26, 2024Jun 26, 2024

    • ARTE

      Public
      GNU Affero General Public License v3.0
      •0•4•0•0•Updated Jun 24, 2024Jun 24, 2024