EIT-NLP / AccuracyParadox-RLHF
[EMNLP 2024 Main] Official implementation of the paper "The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models". (by Yanjun Chen)
☆14Updated 4 months ago
Alternatives and similar repositories for AccuracyParadox-RLHF:
Users that are interested in AccuracyParadox-RLHF are comparing it to the libraries listed below
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆56Updated 8 months ago
- Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue (ACL 2024)☆23Updated 7 months ago
- [EMNLP 2024 Main] Official implementation of the paper "Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mech…☆17Updated 5 months ago
- ☆43Updated 5 months ago
- [EMNLP 2024 Main] Official implementation of the paper "To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimoda…☆14Updated 3 months ago
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆46Updated 3 months ago
- Self-Supervised Alignment with Mutual Information☆16Updated 10 months ago
- [ACL 2024] Code for the paper "ALaRM: Align Language Models via Hierarchical Rewards Modeling"☆25Updated last year
- ☆29Updated 3 months ago
- Official implementation of the paper "Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning". (By Xinghao Chen)☆14Updated last month
- ☆22Updated 8 months ago
- A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models☆18Updated 4 months ago
- The code and data for the paper JiuZhang3.0☆43Updated 10 months ago
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆25Updated last year
- Code and data for "Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue" (ACM TOIS)☆10Updated 5 months ago
- Source code of “Reinforcement Learning with Token-level Feedback for Controllable Text Generation (NAACL 2024)☆11Updated 3 months ago
- [ACL 2024] Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models☆18Updated 8 months ago
- This is a unified platform for implementing and evaluating test-time reasoning mechanisms in Large Language Models (LLMs).☆15Updated 2 months ago
- PyTorch implementation of experiments in the paper Aligning Language Models with Human Preferences via a Bayesian Approach☆31Updated last year
- Code for the paper "Self-Detoxifying Language Models via Toxification Reversal" (EMNLP 2023)☆16Updated last year
- Evaluate the Quality of Critique☆34Updated 10 months ago
- Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (EMNLP 2024 Main Conference)☆57Updated 5 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆52Updated 4 months ago
- ☆59Updated 7 months ago
- The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism☆28Updated 8 months ago
- ☆30Updated last year
- [ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models (LLMs + MCTS + Self-Improvement)☆48Updated last year
- A framework for evolving and testing question-answering datasets with various models.☆14Updated last year
- This the implementation of LeCo☆32Updated 2 months ago
- The code of arxiv paper: "CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis"☆23Updated 2 months ago