A Theoretical Understanding of Self-Correction through In-context Alignment
- URL: http://arxiv.org/abs/2405.18634v2
- Date: Mon, 18 Nov 2024 02:42:23 GMT
- Title: A Theoretical Understanding of Self-Correction through In-context Alignment
- Authors: Yifei Wang, Yuyang Wu, Zeming Wei, Stefanie Jegelka, Yisen Wang,
- Abstract summary: 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.
- Score: 51.622068973630796
- License:
- Abstract: Going beyond mimicking limited human experiences, recent studies show initial evidence that, like humans, large language models (LLMs) are capable of improving their abilities purely by self-correction, i.e., correcting previous responses through self-examination, in certain circumstances. Nevertheless, little is known about how such capabilities arise. In this work, based on a simplified setup akin to an alignment task, we theoretically analyze self-correction from an in-context learning perspective, showing that when LLMs give relatively accurate self-examinations as rewards, they are capable of refining responses in an in-context way. Notably, going beyond previous theories on over-simplified linear transformers, our theoretical construction underpins the roles of several key designs of realistic transformers for self-correction: softmax attention, multi-head attention, and the MLP block. We validate these findings extensively on synthetic datasets. Inspired by these findings, we also illustrate novel applications of self-correction, such as defending against LLM jailbreaks, where a simple self-correction step does make a large difference. We believe that these findings will inspire further research on understanding, exploiting, and enhancing self-correction for building better foundation models.
Related papers
- 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.
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) - Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs [34.203575667558454]
Large Language Models (LLMs) can correct their self-generated responses, but a decline in accuracy after self-correction is also witnessed.
We decompose the self-correction capability into confidence (being confident to correct answers) and critique (turning wrong answers to correct) capabilities.
Our strategy outperforms vanilla SFT in both capabilities and achieves much higher accuracy after self-correction.
arXiv Detail & Related papers (2024-12-27T08:09:11Z) - Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models [10.449015816015566]
Self-improvement is a mechanism in Large Language Model (LLM) pre-training, post-training and test-time inference.
We provide a mathematical formulation for self-improvement, which is largely governed by a quantity which we formalize as the generation-verification gap.
We also examine when self-improvement is possible, an iterative self-improvement procedure, and ways to improve its performance.
arXiv Detail & Related papers (2024-12-03T18:47:26Z) - Is Moral Self-correction An Innate Capability of Large Language Models? A Mechanistic Analysis to Self-correction [5.271054803267951]
We aim to answer two fundamental questions for moral self-correction.
We examine how different self-correction components interact to intervene the embedded morality within hidden states.
We propose a validation framework, self-distinguish, that requires effective self-correction.
arXiv Detail & Related papers (2024-10-27T16:52:21Z) - Large Language Models have Intrinsic Self-Correction Ability [18.79203446847577]
Large language models (LLMs) have attracted significant attention for their exceptional abilities in various natural language processing tasks.
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) - 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) - 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) - A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning.
Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
arXiv Detail & Related papers (2023-11-14T07:13:10Z) - 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.