MikaStars39 / FeatureAlignmentLinks
FeatureAlignment = Alignment + Mechanistic Interpretability
☆29Updated 4 months ago
Alternatives and similar repositories for FeatureAlignment
Users that are interested in FeatureAlignment are comparing it to the libraries listed below
Sorting:
- ☆59Updated 11 months ago
- Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆83Updated 3 weeks ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆114Updated last year
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆58Updated 7 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆63Updated 7 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆62Updated 8 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆76Updated 5 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…☆95Updated 5 months ago
- Collection of Reverse Engineering in Large Model☆34Updated 6 months ago
- BeHonest: Benchmarking Honesty in Large Language Models☆34Updated 11 months ago
- The official repository of the Omni-MATH benchmark.☆85Updated 7 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆175Updated 3 months ago
- ☆48Updated 9 months ago
- ☆65Updated 3 months ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆80Updated 6 months ago
- In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation (ICML 2024)☆61Updated last year
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆142Updated 2 weeks ago
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆61Updated 8 months ago
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆123Updated 3 weeks ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆76Updated 2 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆22Updated 7 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆125Updated 4 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆141Updated this week
- [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*☆110Updated 7 months ago
- ☆117Updated 4 months ago
- ☆203Updated 4 months ago
- ☆60Updated 5 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆58Updated 2 weeks ago
- Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆52Updated 2 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated 8 months ago