paper-with-me

Papers

Learning From Mistakes Makes LLM Better Reasoner

2023-10-31 · Shengnan An, Zexiong Ma, Zeqi Lin, Nanning Zheng, Jian-Guang Lou, Weizhu Chen

Large language models (LLMs) recently exhibited remarkable reasoning capabilities on solving math problems. To further improve their reasoning capabilities, this work explores whether LLMs can LEarn from MistAkes (LEMA), akin to the human learning process. Consider a human student who failed to solve a math problem, he will learn from what mistake he has made and how to correct it. Mimicking this error-driven learning process, LEMA incorporates mistake-correction data pairs during fine-tuning LLMs. Specifically, we first collect inaccurate reasoning paths from various LLMs, and then employ GPT-4 as a ''corrector'' to identify the mistake step, explain the reason for the mistake, correct the mistake and generate the final answer. In addition, we apply a correction-centric evolution strategy that effectively expands the question set for generating correction data. Experiments across various LLMs and reasoning tasks show that LEMA effectively improves CoT-alone fine-tuning. Our further ablations shed light on the non-homogeneous effectiveness between CoT data and correction data. These results suggest a significant potential for LLMs to improve through learning from their mistakes. Our code, models and prompts are publicly available at https://github.com/microsoft/LEMA.

📄 PDF Abstract BibTeX arXiv:2310.20689

Code (1)

microsoft/lema 공식 구현 pytorch

Tasks

GSM8KMathMathematical Reasoning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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…

Similar Papers 제목 키워드 기반

Optimizing Heuristics for Tableau-based OWL Reasoners

2018-10-15 · Razieh Mehri, Volker Haarslev, Hamidreza Chinaei

Optimization techniques play a significant role in improving description logic reasoners covering the Web Ontology Language (OWL). These techniques are essential to speed up these reasoners. Many of the optimization tech…

Large Language Models are Better Reasoners with Self-Verification

2022-12-19 · Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li 외

Recently, with the chain of thought (CoT) prompting, large language models (LLMs), e.g., GPT-3, have shown strong reasoning ability in several natural language processing tasks such as arithmetic, commonsense, and logica…

Arithmetic ReasoningCommon Sense ReasoningFew-Shot LearningLanguage Modelling+1

LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log Analysis

2025-09-25 · Lipeng Ma, Yixuan Li, Weidong Yang, Mingjie Zhou 외 arxiv

Log analysis is crucial for monitoring system health and diagnosing failures in complex systems. Recent advances in large language models (LLMs) offer new opportunities for automated log analysis, leveraging their reason…

Anomaly Detection

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models

2025-02-27 · Yuan Sui, Yufei He, Tri Cao, Simeng Han 외

Large Language Models (LLMs) increasingly rely on prolonged reasoning chains to solve complex tasks. However, this trial-and-error approach often leads to high computational overhead and error propagation, where early mi…

Mathematical ReasoningMulti-Armed Bandits

Composite Learning Units: Generalized Learning Beyond Parameter Updates to Transform LLMs into Adaptive Reasoners

2024-10-09 · Santosh Kumar Radha, Oktay Goktas

Human learning thrives on the ability to learn from mistakes, adapt through feedback, and refine understanding-processes often missing in static machine learning models. In this work, we introduce Composite Learning Unit…

General Knowledge