Tag
Introduces WCM, a World Critic Model that jointly predicts future latent states and estimates values to improve temporal modeling for Vision-Language-Action reinforcement learning, achieving state-of-the-art results across robotic manipulation benchmarks.
This paper systematically evaluates data referencing errors (DREs) in LLMs processing tables and proposes critic-based filtering and rejection sampling to improve answer accuracy. A lightweight 4B-parameter critic model achieves high detection accuracy for DREs.
Critic-R introduces a framework using a critic model to provide introspective feedback between the reasoning agent and retriever, improving agentic search performance at both inference and training time without requiring retraining the agent.
OpenAI introduced CriticGPT, a GPT-4-based model designed to catch errors in ChatGPT's code output. When human trainers use CriticGPT for code review, they outperform those without assistance 60% of the time, addressing a fundamental limitation of RLHF as models become increasingly capable.