IAAR-Shanghai / Awesome-Attention-HeadsLinks
An awesome repository & A comprehensive survey on interpretability of LLM attention heads.
☆380Updated 8 months ago
Alternatives and similar repositories for Awesome-Attention-Heads
Users that are interested in Awesome-Attention-Heads are comparing it to the libraries listed below
Sorting:
- The official repository of our survey paper: "Towards a Unified View of Preference Learning for Large Language Models: A Survey"☆185Updated last year
- [ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation☆177Updated last week
- Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"☆143Updated last year
- All-in-one Web Agent framework for post-training. Start building with a few clicks!☆273Updated 4 months ago
- Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasonin…☆170Updated 11 months ago
- ☆361Updated 5 months ago
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆284Updated 8 months ago
- [ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts☆254Updated last year
- ☆249Updated 6 months ago
- 🏆 ICML 2025 Spotlight☆330Updated 4 months ago
- The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.☆491Updated 3 months ago
- Controllable Text Generation for Large Language Models: A Survey☆193Updated last year
- State-of-the-art Parameter-Efficient MoE Fine-tuning Method☆197Updated last year
- [ACL 2024] RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback.☆185Updated last year
- The repo for In-context Autoencoder☆149Updated last year
- MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models☆451Updated last year
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆189Updated 4 months ago
- A recipe for online RLHF and online iterative DPO.☆536Updated 10 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆70Updated 7 months ago
- Toolkit for Prompt Compression☆282Updated 9 months ago
- [ICLR 2025] Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models☆72Updated 7 months ago
- Collection of Reverse Engineering in Large Model☆35Updated 10 months ago
- Recipes to train the self-rewarding reasoning LLMs.☆227Updated 8 months ago
- Code, benchmark and environment for "ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows"☆118Updated this week
- Repo for the EMNLP'24 Paper "Dual-Space Knowledge Distillation for Large Language Models". A general white-box KD framework for both same…☆60Updated 2 months ago
- A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enab…☆127Updated 3 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆264Updated last year
- This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral).☆365Updated 3 months ago
- This is the repository of DEER, a Dynamic Early Exit in Reasoning method for Large Reasoning Language Models.☆177Updated 4 months ago
- 📜 Paper list on decoding methods for LLMs and LVLMs☆64Updated 2 weeks ago