IAAR-Shanghai / Awesome-Attention-Heads
An awesome repository & A comprehensive survey on interpretability of LLM attention heads.
☆257Updated this week
Related projects ⓘ
Alternatives and complementary repositories for Awesome-Attention-Heads
- The official repository of our survey paper: "Towards a Unified View of Preference Learning for Large Language Models: A Survey"☆145Updated last week
- xFinder: Robust and Pinpoint Answer Extraction for Large Language Models☆143Updated last week
- Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasonin…☆157Updated 2 weeks ago
- [ACL 2024] RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback.☆179Updated 2 months ago
- Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"☆125Updated 7 months ago
- Controllable Text Generation for Large Language Models: A Survey☆140Updated 2 months ago
- Toolkit for Prompt Compression☆244Updated 3 weeks ago
- Benchmarking LLMs via Uncertainty Quantification☆219Updated 9 months ago
- [ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.☆182Updated last month
- Connect agents to live web environments evaluation.☆196Updated last month
- ☆190Updated this week
- MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts☆124Updated 3 weeks ago
- A recipe for online RLHF and online iterative DPO.☆413Updated this week
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆18Updated last week
- Grimoire is All You Need for Enhancing Large Language Models☆116Updated 8 months ago
- Simple PyTorch implementation of "Libra: Building Decoupled Vision System on Large Language Models" (accepted by ICML 2024)☆137Updated 3 weeks ago
- Tool-Planner: Dynamic Solution Tree Planning for Large Language Model with Tool Clustering☆101Updated 4 months ago
- MoH: Multi-Head Attention as Mixture-of-Head Attention☆141Updated last week
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆156Updated 3 months ago
- ☆324Updated last week
- Recipes to train reward model for RLHF.☆788Updated this week
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning"☆91Updated 4 months ago
- Awesome LLM Self-Consistency: a curated list of Self-consistency in Large Language Models☆75Updated 3 months ago
- [🏆Outstanding Paper Award at ACL 2024] MMToM-QA: Multimodal Theory of Mind Question Answering☆126Updated 2 weeks ago
- Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied wit…☆80Updated 3 months ago
- ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆107Updated last week
- [NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models☆208Updated last month
- Official code of the paper "The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models"☆39Updated 2 months ago
- [ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".☆96Updated last week
- Multi-Agent-GPT: 一款基于RAG和agent构建的多模态专家助手GPT。它集成了文本、图像和音频等模态工具。支持本地部署和私有数据库建设。☆221Updated 8 months ago