yifan-h / MechanisticProbeLinks
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
Sorting:
- [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization☆88Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆110Updated last month
- ☆50Updated 11 months ago
- Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"☆75Updated 3 months ago
- ☆167Updated 4 months ago
- This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"☆69Updated 5 months ago
- [2025-TMLR] A Survey on the Honesty of Large Language Models☆59Updated 10 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆30Updated 7 months ago
- ☆207Updated 6 months ago
- ☆67Updated 5 months ago
- [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct☆186Updated 8 months ago
- Implementation of the MATRIX framework (ICML 2024)☆60Updated last year
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆128Updated 6 months ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆164Updated last week
- A comprehensive collection of process reward models.☆110Updated this week
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆64Updated 10 months ago
- AdaRFT: Efficient Reinforcement Finetuning via Adaptive Curriculum Learning☆46Updated 3 months ago
- Benchmarking LLMs' Gaming Ability in Multi-Agent Environments☆88Updated 5 months ago
- Repo for Anonymous purpose, pls don't distribute☆10Updated last year
- ☆19Updated 7 months ago
- Official code for paper "SPA-RL: Reinforcing LLM Agent via Stepwise Progress Attribution"☆43Updated 3 weeks ago
- Project of ACL 2025 "UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models"☆13Updated 6 months ago
- [AI4MATH@ICML2025] Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs☆40Updated 4 months ago
- This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by g…☆36Updated 2 months ago
- [ICLR 25 Oral] RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style☆62Updated 2 months ago
- Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts☆25Updated last year
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated 10 months ago
- The rule-based evaluation subset and code implementation of Omni-MATH☆23Updated 9 months ago
- Source code for our paper: "ARIA: Training Language Agents with Intention-Driven Reward Aggregation".☆22Updated last month
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆81Updated 4 months ago