On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and
Latent Concept

On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept

4 June 2024

Guangliang Liu

ArXiv (abs)PDF HTML

Papers citing "On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept"

7 / 7 papers shown

Title
Perception in Reflection Yana Wei Liang Zhao Kangheng Lin En Yu Yuang Peng ... Jianjian Sun Haoran Wei Zheng Ge Xiangyu Zhang Vishal M. Patel 135 1 0 09 Apr 2025
Rethinking Prompt-based Debiasing in Large Language Models Xinyi Yang Runzhe Zhan Derek F. Wong Shu Yang Junchao Wu Lidia S. Chao ALM 181 1 0 12 Mar 2025
Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability Chenhui Xu Dancheng Liu Jiajie Li Amir Nassereldine Zhaohui Li Jinjun Xiong LRM 101 0 0 05 Mar 2025
Smaller Large Language Models Can Do Moral Self-Correction Guangliang Liu Zhiyu Xue Rongrong Wang K. Johnson Kristen Marie Johnson LRM 107 0 0 30 Oct 2024
Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis Guang-Da Liu Haitao Mao Jiliang Tang K. Johnson LRM 97 8 0 21 Jul 2024
When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs Ryo Kamoi Yusen Zhang Nan Zhang Jiawei Han Rui Zhang LRM 173 85 0 03 Jun 2024
ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence Kevin Wu Eric Wu James Zou AAML 167 48 0 16 Apr 2024