Skip to content
Change the repository type filter

All

    Repositories list

    • [NeurIPS 2024 Workshop on Compositional Learning]This is an official repository for the paper "How language models extrapolate outside the training data: A case study in Textualized Gridworld."
      Python
      0000Updated Dec 5, 2024Dec 5, 2024
    • Janus

      Public
      [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages
      Python
      Apache License 2.0
      33800Updated Dec 4, 2024Dec 4, 2024
    • [EMNLP 2024] Official implementation of "Hierarchical Deconstruction of LLM Reasoning: A Graph-Based Framework for Analyzing Knowledge Utilization"
      Python
      Apache License 2.0
      32000Updated Dec 4, 2024Dec 4, 2024
    • JavaScript
      0000Updated Dec 4, 2024Dec 4, 2024
    • This repository is the official implementation of Generative Context Distillation.
      Python
      0100Updated Dec 1, 2024Dec 1, 2024
    • Python
      Apache License 2.0
      0400Updated Nov 25, 2024Nov 25, 2024
    • [ACL 2024] LangBridge: Multilingual Reasoning Without Multilingual Supervision
      Python
      78200Updated Oct 30, 2024Oct 30, 2024
    • KtrlF

      Public
      [NAACL 2024] Official repository for "KTRL+F: Knowledge-Augmented In-Document Search"
      Python
      42010Updated Oct 11, 2024Oct 11, 2024
    • Python
      Apache License 2.0
      01400Updated Oct 5, 2024Oct 5, 2024
    • Python
      11000Updated Sep 13, 2024Sep 13, 2024
    • GAP

      Public
      [ACL 2023] Gradient Ascent Post-training Enhances Language Model Generalization
      Python
      Apache License 2.0
      42810Updated Sep 12, 2024Sep 12, 2024
    • Python
      1800Updated Aug 23, 2024Aug 23, 2024
    • Volcano

      Public
      [NAACL 2024] Vision language model that reduces hallucinations through self-feedback guided revision. Visualizes attentions on image features for interpretation.
      Python
      44311Updated Aug 21, 2024Aug 21, 2024
    • IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our focuses on user-aligned instructions tailored to each query instance.
      Python
      MIT License
      43010Updated Jun 13, 2024Jun 13, 2024
    • ClaimDiff

      Public
      2600Updated Mar 4, 2024Mar 4, 2024
    • FLASK

      Public
      [ICLR 2024 Spotlight] FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
      Python
      1821231Updated Dec 24, 2023Dec 24, 2023
    • [EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning
      Python
      1021731Updated Oct 31, 2023Oct 31, 2023
    • SelFee

      Public
      Official codebase for "SelFee: Iterative Self-Revising LLM Empowered by Self-Feedback Generation"
      Python
      Apache License 2.0
      2022200Updated Jun 6, 2023Jun 6, 2023
    • Summarization module based on KoBART
      Python
      MIT License
      91000Updated Sep 14, 2022Sep 14, 2022
    • 0000Updated Mar 29, 2022Mar 29, 2022