Preprint2024
Critique-out-loud reward models
Unknown
Introduces Critique-out-Loud (CLoud) reward models that are trained to generate critiques, improving reward modeling for LLMs.
0Aug 1, 2024
arXiv
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
6 papersPreprint2025
Beyond Preferences in AI Alignment: T. Zhi-Xuan et al.
Unknown
This paper critiques the dominant 'preferentist' approach to AI alignment and proposes a reframing of alignment targets beyond human preferences.
0Jan 1, 2025Alignment
Preprint2024
CriticGPT
Unknown
CriticGPT uses RLHF to train a GPT-4-based model that critiques ChatGPT code outputs, helping humans catch bugs more accurately.
0Jun 1, 2024
Preprint2023
Multiagent Debate
Unknown
Proposes a multi-agent debate framework where multiple language models iteratively critique and refine answers to improve factual accuracy and reasoning.
0May 1, 2023Reasoning
Preprint2025
Critique Fine-Tuning
Unknown
Critique Fine-Tuning trains models to critique noisy responses, improving reasoning more than imitating correct answers.
0Jan 1, 2025Reasoning
arXiv
Preprint2024
Direct Judgement Preference Optimization
Unknown
Proposes Direct Judgement Preference Optimization to enhance LLM judges via Chain-of-Thought Critique, Standard Judgement, and Response Deduction for rating, comparison, and classification.
0Sep 1, 2024Chain Of Thought