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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations