Alternatives and similar repositories for Token-level-Direct-Preference-Optimization

Users that are interested in Token-level-Direct-Preference-Optimization are comparing it to the libraries listed below

• sanowl / Self-Correcting-LLM--Reinforcement-Learning-
  This my attempt to create Self-Correcting-LLM based on the paper Training Language Models to Self-Correct via Reinforcement Learning by g…
  ☆35Updated 2 months ago
• liziniu / ReMax
  Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)
  ☆193Updated last year
• Linear95 / APO
  Code for ACL2024 paper - Adversarial Preference Optimization (APO).
  ☆56Updated last year
• ZHZisZZ / modpo
  [ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
  ☆86Updated last year
• PKU-Alignment / aligner
  [NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct
  ☆184Updated 7 months ago
• PRIME-RL / ImplicitPRM
  Repo of paper "Free Process Rewards without Process Labels"
  ☆162Updated 6 months ago
• thu-ml / Noise-Contrastive-Alignment
  Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)
  ☆57Updated 10 months ago
• PRIME-RL / Entropy-Mechanism-of-RL
  The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.
  ☆320Updated 2 months ago
• sail-sg / CPO
  [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.
  ☆129Updated 5 months ago
• tongyx361 / Awesome-LLM4Math
  Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied wit…
  ☆137Updated last year
• CJReinforce / PURE
  Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"
  ☆136Updated last month
• WooooDyy / MathCritique
  Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".
  ☆56Updated 9 months ago
• IAAR-Shanghai / xVerify
  xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
  ☆128Updated 4 months ago
• kanishkg / cognitive-behaviors
  ☆205Updated 5 months ago
• WeiXiongUST / Building-Math-Agents-with-Multi-Turn-Iterative-Preference-Learning
  This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DP…
  ☆29Updated 9 months ago
• RLHFlow / RAFT
  This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…
  ☆37Updated 11 months ago
• Dereck0602 / Awesome_Test_Time_LLMs
  ☆122Updated 6 months ago
• YuxiXie / MCTS-DPO
  This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.
  ☆321Updated last year
• hahahawu / Long-to-Short-via-Model-Merging
  Model merging is a highly efficient approach for long-to-short reasoning.
  ☆80Updated 3 months ago
• CMU-AIRe / MRT
  Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".
  ☆104Updated last month
• Edward-Sun / easy-to-hard
  Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
  ☆123Updated last year
• hkust-nlp / dart-math
  [NeurIPS'24] Official code for *🎯DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving*
  ☆113Updated 9 months ago
• FreedomIntelligence / OVM
  ☆68Updated last year
• rookie-joe / AutoPSV
  ☆49Updated 10 months ago
• SparkJiao / dpo-trajectory-reasoning
  [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".
  ☆81Updated 8 months ago
• GAIR-NLP / LIMR
  ☆209Updated 6 months ago
• thu-wyz / inference_scaling
  ☆74Updated 9 months ago
• Yifan-Song793 / ETO
  Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents (ACL 2024 Main Conference)
  ☆149Updated 10 months ago
• yyDing1 / ScaleQuest
  [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.
  ☆64Updated 10 months ago
• AlphaPav / mem-kk-logic
  On Memorization of Large Language Models in Logical Reasoning
  ☆71Updated 5 months ago