paper-with-me

Papers

Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning

2024-10-14 · Kuofeng Gao, Huanqia Cai, Qingyao Shuai, Dihong Gong, Zhifeng Li

Accurate mathematical reasoning with Large Language Models (LLMs) is crucial in revolutionizing domains that heavily rely on such reasoning. However, LLMs often encounter difficulties in certain aspects of mathematical reasoning, leading to flawed reasoning and erroneous results. To mitigate these issues, we introduce a novel mechanism, the Chain of Self-Correction (CoSC), specifically designed to embed self-correction as an inherent ability in LLMs, enabling them to validate and rectify their own results. The CoSC mechanism operates through a sequence of self-correction stages. In each stage, the LLMs generate a program to address a given problem, execute this program using program-based tools to obtain an output, subsequently verify this output. Based on the verification, the LLMs either proceed to the next correction stage or finalize the answer. This iterative self-correction process allows the LLMs to refine their reasoning steps and improve the accuracy of their mathematical reasoning. To enable the CoSC mechanism at a low cost, we employ a two-phase finetuning approach. In the first phase, the LLMs are trained with a relatively small volume of seeding data generated from GPT-4, establishing an initial CoSC capability. In the second phase, the CoSC capability is further enhanced by training with a larger volume of self-generated data using the trained model in the first phase, without relying on the paid GPT-4. Our comprehensive experiments demonstrate that CoSC significantly improves performance on traditional mathematical datasets among existing open-source LLMs. Notably, our CoSC-Code-34B model achieved a 53.5% score on MATH, the most challenging mathematical reasoning dataset in the public domain, surpassing the performance of well-established models such as ChatGPT, GPT-4, and even multi-modal LLMs like GPT-4V, Gemini-1.0 Pro, and Gemini-1.0 Ultra.

📄 PDF Abstract BibTeX arXiv:2410.10735

Code (0)

등록된 구현이 없습니다.

Tasks

MathMathematical Reasoning

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Understanding the Dark Side of LLMs' Intrinsic Self-Correction

2024-12-19 · Qingjie Zhang, Han Qiu, Di Wang, Haoting Qian 외

Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic self-correction fails without oracle label…

Large Language Models Cannot Self-Correct Reasoning Yet

2023-10-03 · Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng 외

Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities across various applications. Nevertheless, concerns persist regarding the accuracy and appropr…

Text Generation

Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction

2026-01-09 · Hongjin Kim, Jaewook Lee, Kiyoung Lee, Jong-hun Shin 외 arxiv

Large Language Models (LLMs) demonstrate strong reasoning and self-correction abilities in high-resource languages like English, but their performance remains limited in low-resource languages such as Korean. In this stu…

Reinforcement LearningMathematical Reasoning

An Explanation of Intrinsic Self-Correction via Linear Representations and Latent Concepts

2025-05-17 · Yu-Ting Lee, Hui-Ying Shih, Fu-Chieh Chang, Pei-Yuan Wu

We provide an explanation for the performance gains of intrinsic self-correction, a process where a language model iteratively refines its outputs without external feedback. More precisely, we investigate how prompting i…

Concept AlignmentLanguage ModelingLanguage Modelling

Is Moral Self-correction An Innate Capability of Large Language Models? A Mechanistic Analysis to Self-correction

2024-10-27 · Zimo Qi, Guangliang Liu, Kristen Marie Johnson, Lu Cheng

Though intensive attentions to the self-correction capability of Large Language Models (LLMs), the underlying mechanism of this capability is still under-explored. In this paper, we aim to answer two fundamental question…