{"ID":2899762,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.00985","arxiv_id":"2507.00985","title":"Discourse Heuristics For Paradoxically Moral Self-Correction","abstract":"Moral self-correction has emerged as a promising approach for aligning the output of Large Language Models (LLMs) with human moral values. However, moral self-correction techniques are subject to two primary paradoxes. First, despite empirical and theoretical evidence to support the effectiveness of self-correction, this LLM capability only operates at a superficial level. Second, while LLMs possess the capability of self-diagnosing immoral aspects of their output, they struggle to identify the cause of this moral inconsistency during their self-correction process. To better understand and address these paradoxes, we analyze the discourse constructions in fine-tuning corpora designed to enhance moral self-correction, uncovering the existence of the heuristics underlying effective constructions. We demonstrate that moral self-correction relies on discourse constructions that reflect heuristic shortcuts, and that the presence of these heuristic shortcuts during self-correction leads to inconsistency when attempting to enhance both self-correction and self-diagnosis capabilities jointly. Based on our findings, we propose a solution to improve moral self-correction by leveraging the heuristics of curated datasets. We also highlight the generalization challenges of this capability, particularly in terms of learning from situated context and model scales.","short_abstract":"Moral self-correction has emerged as a promising approach for aligning the output of Large Language Models (LLMs) with human moral values. However, moral self-correction techniques are subject to two primary paradoxes. First, despite empirical and theoretical evidence to support the effectiveness of self-correction, th...","url_abs":"https://arxiv.org/abs/2507.00985","url_pdf":"https://arxiv.org/pdf/2507.00985v2","authors":"[\"Guangliang Liu\",\"Zimo Qi\",\"Xitong Zhang\",\"Kristen Marie Johnson\"]","published":"2025-07-01T17:36:41Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}