On the Convergence of Moral Self-Correction in Large Language Models

• URL: http://arxiv.org/abs/2510.07290v3
• Date: Sun, 26 Oct 2025 19:28:05 GMT
• Title: On the Convergence of Moral Self-Correction in Large Language Models
• Authors: Guangliang Liu, Haitao Mao, Bochuan Cao, Zhiyu Xue, Xitong Zhang, Rongrong Wang, Kristen Marie Johnson,
• Abstract summary: Large Language Models (LLMs) are able to improve their responses when instructed to do so.<n>LLMs must rely on their internal knowledge to improve response quality, a process referred to as intrinsic self-correction.<n>We reveal a key characteristic of intrinsic self-correction: performance convergence through multi-round interactions.
• Score: 26.724972162483855
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. When instructions provide only a general and abstract goal without specific details about potential issues in the response, LLMs must rely on their internal knowledge to improve response quality, a process referred to as intrinsic self-correction. The empirical success of intrinsic self-correction is evident in various applications, but how and why it is effective remains unknown. Focusing on moral self-correction in LLMs, we reveal a key characteristic of intrinsic self-correction: performance convergence through multi-round interactions; and provide a mechanistic analysis of this convergence behavior. Based on our experimental results and analysis, we uncover the underlying mechanism of convergence: consistently injected self-correction instructions activate moral concepts that reduce model uncertainty, leading to converged performance as the activated moral concepts stabilize over successive rounds. This paper demonstrates the strong potential of moral self-correction by showing that it exhibits a desirable property of converged performance.

Related papers

• Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning [52.99434388759101]
  We propose a self-evolving vision-language agent that achieves continual improvement with tool-integrated reasoning.<n>Agent0-VL incorporates tool usage not only into reasoning but also into self-evaluation and self-repair.<n>Our experiments show that Agent0-VL achieves an 12.5% improvement over the base model.
  arXiv  Detail & Related papers  (2025-11-25T04:15:14Z)
• Discourse Heuristics For Paradoxically Moral Self-Correction [6.360181137608509]
  Moral self-correction has emerged as a promising approach for aligning the output of Large Language Models with human moral values.<n>We show that moral self-correction relies on discourse constructions that reflect shortcuts.<n>We propose a solution to improve moral self-correction by leveraging the generalizations of curated datasets.
  arXiv  Detail & Related papers  (2025-07-01T17:36:41Z)
• Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards [67.86091419220816]
  Large Language Models (LLMs) show great promise in complex reasoning.<n>A prevalent issue is superficial self-reflection'', where models fail to robustly verify their own outputs.<n>We introduce RISE (Reinforcing Reasoning with Self-Verification), a novel online RL framework designed to tackle this.
  arXiv  Detail & Related papers  (2025-05-19T17:59:31Z)
• ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification [53.80183105328448]
  Refine via Intrinsic Self-Verification (ReVISE) is an efficient framework that enables LLMs to self-correct their outputs through self-verification.<n>Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.
  arXiv  Detail & Related papers  (2025-02-20T13:50:02Z)
• Self-correction is Not An Innate Capability in Large Language Models: A Case Study of Moral Self-correction [8.61034573238112]
  We argue that moral self-correction is not an innate capability of Large Language Models (LLMs)<n>We conduct a mechanistic analysis of how key components of self-correction, such as Chain-of-Thought (CoT) reasoning and external feedback, interact to enable moral self-correction.
  arXiv  Detail & Related papers  (2024-10-27T16:52:21Z)
• On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept [36.27550578296276]
  Large Language Models (LLMs) are able to improve their responses when instructed to do so, a capability known as self-correction. In intrinsic self-correction is evident in various applications, but how and why it is effective remains unknown. We show that intrinsic self-correction can be progressively improved, allowing it to approach a converged state.
  arXiv  Detail & Related papers  (2024-06-04T14:55:43Z)
• A Theoretical Understanding of Self-Correction through In-context Alignment [51.622068973630796]
  Large language models (LLMs) are capable of improving their abilities purely by self-correction. We show that when LLMs give relatively accurate self-examinations as rewards, they are capable of refining responses in an in-context way. Inspired by these findings, we also illustrate applications of self-correction, such as defending against LLM jailbreaks.
  arXiv  Detail & Related papers  (2024-05-28T22:33:02Z)
• Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models [23.42725642076256]
  Large Language Models (LLMs) have catalyzed an increasing interest in their self-correction capabilities. This paper presents a comprehensive investigation into the intrinsic self-correction of LLMs. We develop an "If-or-Else" (IoE) prompting framework, designed to guide LLMs in assessing their own "confidence"
  arXiv  Detail & Related papers  (2024-02-19T21:38:02Z)
• Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation [71.91287418249688]
  Large language models (LLMs) often struggle with factual inaccuracies, even when they hold relevant knowledge. We leverage the self-evaluation capability of an LLM to provide training signals that steer the model towards factuality. We show that the proposed self-alignment approach substantially enhances factual accuracy over Llama family models across three key knowledge-intensive tasks.
  arXiv  Detail & Related papers  (2024-02-14T15:52:42Z)
• N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics [5.516095889257118]
  We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback.
  arXiv  Detail & Related papers  (2023-10-28T11:22:22Z)
• Large Language Models Cannot Self-Correct Reasoning Yet [78.16697476530994]
  Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities. Concerns persist regarding the accuracy and appropriateness of their generated content. A contemporary methodology, self-correction, has been proposed as a remedy to these issues.
  arXiv  Detail & Related papers  (2023-10-03T04:56:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.