Smaller Large Language Models Can Do Moral Self-Correction

• URL: http://arxiv.org/abs/2410.23496v1
• Date: Wed, 30 Oct 2024 22:58:57 GMT
• Title: Smaller Large Language Models Can Do Moral Self-Correction
• Authors: Guangliang Liu, Zhiyu Xue, Rongrong Wang, Kristen Marie Johnson,
• Abstract summary: Self-correction is one of the most amazing emerging capabilities of Large Language Models (LLMs) Moral self-correction is a post-hoc approach correcting unethical generations without requiring a gradient update. Previous works have shown that LLMs can self-debias, and it has been reported that small models, i.e., those with less than 22B parameters, are not capable of moral self-correction.
• Score: 7.899707459486236
• License:
• Abstract: Self-correction is one of the most amazing emerging capabilities of Large Language Models (LLMs), enabling LLMs to self-modify an inappropriate output given a natural language feedback which describes the problems of that output. Moral self-correction is a post-hoc approach correcting unethical generations without requiring a gradient update, making it both computationally lightweight and capable of preserving the language modeling ability. Previous works have shown that LLMs can self-debias, and it has been reported that small models, i.e., those with less than 22B parameters, are not capable of moral self-correction. However, there is no direct proof as to why such smaller models fall short of moral self-correction, though previous research hypothesizes that larger models are skilled in following instructions and understanding abstract social norms. In this paper, we empirically validate this hypothesis in the context of social stereotyping, through meticulous prompting. Our experimental results indicate that (i) surprisingly, 3.8B LLMs with proper safety alignment fine-tuning can achieve very good moral self-correction performance, highlighting the significant effects of safety alignment; and (ii) small LLMs are indeed weaker than larger-scale models in terms of comprehending social norms and self-explanation through CoT, but all scales of LLMs show bad self-correction performance given unethical instructions.

Related papers

• Large Language Models have Intrinsic Self-Correction Ability [16.831123666582755]
  Large language models suffer from hallucinations that will cause performance degradation. One promising solution to improve the LLMs' performance is to ask LLMs to revise their answer after generation. In intrinsic self-correction is considered a promising direction because it does not utilize external knowledge.
  arXiv  Detail & Related papers  (2024-06-21T22:29:40Z)
• 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)
• Small Language Models Need Strong Verifiers to Self-Correct Reasoning [69.94251699982388]
  Self-correction has emerged as a promising solution to boost the reasoning performance of large language models (LLMs) This work explores whether small (= 13B) language models (LMs) have the ability of self-correction on reasoning tasks with minimal inputs from stronger LMs.
  arXiv  Detail & Related papers  (2024-04-26T03:41:28Z)
• Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement [75.7148545929689]
  Large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We formally define LLM's self-bias - the tendency to favor its own generation. We analyze six LLMs on translation, constrained text generation, and mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-02-18T03:10:39Z)
• Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes [73.12947922129261]
  We leverage the zero-shot capabilities of large language models to reduce stereotyping. We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
  arXiv  Detail & Related papers  (2024-02-03T01:40:11Z)
• Small Language Model Can Self-correct [42.76612128849389]
  We introduce the underlineIntrinsic underlineSelf-underlineCorrection (ISC) in generative language models, aiming to correct the initial output of LMs in a self-triggered manner. We conduct experiments using LMs with parameters sizes ranging from 6 billion to 13 billion in two tasks, including commonsense reasoning and factual knowledge reasoning.
  arXiv  Detail & Related papers  (2024-01-14T14:29:07Z)
• Psychometric Predictive Power of Large Language Models [32.31556074470733]
  We find that instruction tuning does not always make large language models human-like from a cognitive modeling perspective. Next-word probabilities estimated by instruction-tuned LLMs are often worse at simulating human reading behavior than those estimated by base LLMs.
  arXiv  Detail & Related papers  (2023-11-13T17:19:14Z)
• Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis [127.85293480405082]
  The rapid development of large language models (LLMs) has not only provided numerous opportunities but also presented significant challenges. Existing alignment methods usually direct LLMs toward the favorable outcomes by utilizing human-annotated, flawless instruction-response pairs. This study proposes a novel alignment technique based on mistake analysis, which deliberately exposes LLMs to erroneous content to learn the reasons for mistakes and how to avoid them.
  arXiv  Detail & Related papers  (2023-10-16T14:59:10Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

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.