RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs (2023.acl-long)
Copied to clipboard
| Challenge: | Despite their success, even the largest language models make mistakes. |
| Approach: | They propose a framework where one language model can generate critiques to improve its peer's performance. |
| Outcome: | The proposed framework improves the performance of a fixed model 200 times its size by 10% over other models. |
Similar Papers
Training Language Models to Critique With Multi-agent Feedback (2025.findings-emnlp)
Copied to clipboard
Tian Lan, Wenwei Zhang, Chengqi Lyu, Shuaibin Li, Chen Xu, Heyan Huang, Dahua Lin, Xian-Ling Mao, Kai Chen
| Challenge: | utilizing human annotations can enhance critique ability, but model-generated critiques suffer from inherent flaws due to complexity of critique . a new framework that leverages multi-agent feedback improves critique ability . |
| Approach: | They propose a framework that leverages multi-agent feedback to improve critique ability . they propose to use supervised fine-tuning and reinforcement learning to improve this capability . |
| Outcome: | The proposed framework improves critique ability in both supervised fine-tuning and reinforcement learning stages. |
CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)
Copied to clipboard
Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang
| Challenge: | Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references. |
| Approach: | They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings. |
| Outcome: | The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading. |
Removing RLHF Protections in GPT-4 via Fine-Tuning (2024.naacl-short)
Copied to clipboard
| Challenge: | Large language models (LLMs) have increased in their capabilities, which increases their potential for dual use. |
| Approach: | They show that fine-tuning can remove RLHFprotections with as few as 340 examples and a 95% success rate. |
| Outcome: | The proposed method removes RLHFprotections with as few as 340 examples and a 95% success rate on non-censored outputs. |
Large Language Models with Reinforcement Learning from Human Feedback Approach for Enhancing Explainable Sexism Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have significantly improved text comprehension. |
| Approach: | They propose a Reinforcement Learning from Human Feedback (RLHF) based fine-tuning framework for sexism detection that leverages contextual learning to understand and apply instructions to new scenarios without additional training. |
| Outcome: | The proposed framework outperforms existing models on three EDOS tasks and scores 0.8681 on binary sexism detection, 0.6829 on category classification of sexists and 0.4722 on task C. |
Adaptive Reinforcement Tuning Language Models as Hard Data Generators for Sentence Representation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods use contrastive learning (CL) to learn effective sentence representations, but require extensive human annotation. |
| Approach: | They propose a reinforcement learning approach for fine-tuning small-parameter LLMs to generate high-quality hard contrastive data without human feedback. |
| Outcome: | The proposed method achieves state-of-the-art on seven semantic text similarity tasks. |
Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic (2024.emnlp-main)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences, but the sparsity of these signals can lead to inefficient and unstable learning. |
| Approach: | They propose a framework that utilizes the critique capability of Large Language Models to produce intermediate-step rewards during RL training. |
| Outcome: | The proposed framework improves sample efficiency and the overall performance of the policy model, supported by both automatic and human evaluation. |
trlX: A Framework for Large Scale Reinforcement Learning from Human Feedback (2023.emnlp-main)
Copied to clipboard
Alexander Havrilla, Maksym Zhuravinskyi, Duy Phung, Aman Tiwari, Jonathan Tow, Stella Biderman, Quentin Anthony, Louis Castricato
| Challenge: | Current RLHF paradigms rely on Proximal Policy Optimization (PPO), which quickly becomes a challenge to implement and scale up to large architectures. |
| Approach: | They propose an open-source framework for reinforcement learning from human feedback . it allows for offline fine-tuning of large language models . |
| Outcome: | The framework can be used to fine-tune models up to and exceeding 70 billion parameters. |
Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue (D19-1)
Copied to clipboard
| Challenge: | Existing methods to generate natural language for task-oriented dialogues lack naturalness and variation in language. |
| Approach: | They propose a multi-task learning framework for natural language generation that explicitly targets for naturalness in generated responses via an unconditioned language model. |
| Outcome: | The proposed framework outperforms existing models across multiple datasets in the study of natural language generation. |
Aligning Large Language Models via Fully Self-Synthetic Data (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to reinforcement learning from human feedback (RLHF) require expensive human-annotated datasets and proprietary models like GPT-4 to annotate preference pairs. |
| Approach: | They propose a self-synthetic framework for LLM alignment where all training data, including prompts (i.e., user queries), responses, and preferences, are generated by the model itself. |
| Outcome: | The proposed framework enhances the model’s chat capabilities on standard benchmarks like AlpacaEval 2.0 while maintaining strong performance on downstream objective tasks. |
Self-Generated Critiques Boost Reward Modeling for Language Models (2025.naacl-long)
Copied to clipboard
Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, Rui Hou
| Challenge: | Existing reward models produce scalar scores and struggle to incorporate critiques in a natural language format. |
| Approach: | They propose a framework that predicts critiques and rewards using self-generated critiques without extra supervision. |
| Outcome: | The proposed framework improves reward modeling accuracy by 3.7%-7.3% compared to standard reward models and LLM judges. |