Learning to Check: Unleashing Potentials for Self-Correction in Large Language Models
- URL: http://arxiv.org/abs/2402.13035v3
- Date: Mon, 17 Jun 2024 15:24:29 GMT
- Title: Learning to Check: Unleashing Potentials for Self-Correction in Large Language Models
- Authors: Che Zhang, Zhenyang Xiao, Chengcheng Han, Yixin Lian, Yuejian Fang,
- Abstract summary: We aim to enhance the self-checking capabilities of large language models (LLMs) by constructing training data for checking tasks.
We propose a specialized checking format called "Step CoT Check"
Experiments demonstrate that fine-tuning with the "Step CoT Check" format significantly improves the self-checking and self-correction abilities of LLMs.
- Score: 5.463333911506443
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Self-correction has achieved impressive results in enhancing the style and security of the generated output from large language models (LLMs). However, recent studies suggest that self-correction might be limited or even counterproductive in reasoning tasks due to LLMs' difficulties in identifying logical mistakes. In this paper, we aim to enhance the self-checking capabilities of LLMs by constructing training data for checking tasks. Specifically, we apply the Chain of Thought (CoT) methodology to self-checking tasks, utilizing fine-grained step-level analyses and explanations to assess the correctness of reasoning paths. We propose a specialized checking format called "Step CoT Check". Following this format, we construct a checking-correction dataset that includes detailed step-by-step analysis and checking. Then we fine-tune LLMs to enhance their error detection and correction abilities. Our experiments demonstrate that fine-tuning with the "Step CoT Check" format significantly improves the self-checking and self-correction abilities of LLMs across multiple benchmarks. This approach outperforms other formats, especially in locating the incorrect position, with greater benefits observed in larger models. For reproducibility, all the datasets and code are provided in https://github.com/bammt/Learn-to-check.
Related papers
- Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
Large language models (LLMs) struggle with consistent and accurate reasoning.
LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors.
We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
arXiv Detail & Related papers (2024-10-05T05:21:48Z) - S$^3$c-Math: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners [23.713779973116733]
Self-correction is a method that can stimulate the potential reasoning abilities of large language models (LLMs)
We propose S$3$c-Math, which are able to perform Spontaneous Step-level Self-correction for Mathematical reasoning.
arXiv Detail & Related papers (2024-09-03T01:40:21Z) - DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity.
Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data.
Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
arXiv Detail & Related papers (2024-06-25T04:27:53Z) - 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) - LLMs cannot find reasoning errors, but can correct them given the error location [0.9017736137562115]
Poor self-correction performance stems from LLMs' inability to find logical mistakes, rather than their ability to correct a known mistake.
We benchmark several state-of-the-art LLMs on their mistake-finding ability and demonstrate that they generally struggle with the task.
We show that it is possible to obtain mistake location information without ground truth labels or in-domain training data.
arXiv Detail & Related papers (2023-11-14T20:12:38Z) - Learning From Mistakes Makes LLM Better Reasoner [106.48571828587728]
Large language models (LLMs) recently exhibited remarkable reasoning capabilities on solving math problems.
This work explores whether LLMs can LEarn from MistAkes (LEMA), akin to the human learning process.
arXiv Detail & Related papers (2023-10-31T17:52:22Z) - SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step
Reasoning [55.76083560152823]
SelfCheck is a general-purpose zero-shot verification schema for recognizing errors in step-by-step reasoning.
We test SelfCheck on three datasets (GSM8K, MathQA, and MATH) and find that it successfully recognizes errors and, in turn, increases final answer accuracies.
arXiv Detail & Related papers (2023-08-01T10:31:36Z) - Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models [75.75038268227554]
Self-Checker is a framework comprising a set of plug-and-play modules that facilitate fact-checking.
This framework provides a fast and efficient way to construct fact-checking systems in low-resource environments.
arXiv Detail & Related papers (2023-05-24T01:46:07Z)
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.