yifan-h / MechanisticProbe
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models
☆14Updated last year
Alternatives and similar repositories for MechanisticProbe:
Users that are interested in MechanisticProbe are comparing it to the libraries listed below
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆107Updated last week
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆119Updated 6 months ago
- ☆30Updated 5 months ago
- ☆43Updated 5 months ago
- ☆28Updated last month
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆50Updated 2 weeks ago
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆37Updated 3 weeks ago
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆72Updated 7 months ago
- Interpretable Contrastive Monte Carlo Tree Search Reasoning☆46Updated 4 months ago
- The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"☆37Updated last year
- Code for the paper <SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning>☆48Updated last year
- Implementation of the ICML 2024 paper "Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning" pr…☆95Updated last year
- ☆65Updated last year
- [𝐄𝐌𝐍𝐋𝐏 𝐅𝐢𝐧𝐝𝐢𝐧𝐠𝐬 𝟐𝟎𝟐𝟒 & 𝐀𝐂𝐋 𝟐𝟎𝟐𝟒 𝐍𝐋𝐑𝐒𝐄 𝐎𝐫𝐚𝐥] 𝘌𝘯𝘩𝘢𝘯𝘤𝘪𝘯𝘨 𝘔𝘢𝘵𝘩𝘦𝘮𝘢𝘵𝘪𝘤𝘢𝘭 𝘙𝘦𝘢𝘴𝘰𝘯𝘪𝘯…☆49Updated 10 months ago
- Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)☆57Updated 5 months ago
- ☆31Updated 3 weeks ago
- This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by g…☆32Updated 3 months ago
- ☆37Updated last year
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆56Updated 3 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆52Updated 4 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆52Updated 4 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆28Updated last week
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆71Updated 3 weeks ago
- ☆39Updated 4 months ago
- A Survey on the Honesty of Large Language Models☆56Updated 3 months ago
- GenRM-CoT: Data release for verification rationales☆53Updated 5 months ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆167Updated 2 months ago
- Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering☆58Updated 3 months ago
- ☆129Updated last week