paper-with-me

Papers

Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus

2024-11-19 · Terufumi Morishita, Gaku Morio, Atsuki Yamaguchi, Yasuhiro Sogawa

Large language models (LLMs) are capable of solving a wide range of tasks, yet they have struggled with reasoning. To address this, we propose $\textbf{Additional Logic Training (ALT)}$, which aims to enhance LLMs' reasoning capabilities by program-generated logical reasoning samples. We first establish principles for designing high-quality samples by integrating symbolic logic theory and previous empirical insights. Then, based on these principles, we construct a synthetic corpus named $\textbf{Formal Logic Deduction Diverse}$ ($\textbf{FLD}$$_{\times 2}$), comprising numerous samples of multi-step deduction with unknown facts, diverse reasoning rules, diverse linguistic expressions, and challenging distractors. Finally, we empirically show that ALT on FLD$_{\times2}$ substantially enhances the reasoning capabilities of state-of-the-art LLMs, including LLaMA-3.1-70B. Improvements include gains of up to 30 points on logical reasoning benchmarks, up to 10 points on math and coding benchmarks, and 5 points on the benchmark suite BBH.

📄 PDF Abstract BibTeX arXiv:2411.12498

Code (2)

hitachi-nlp/fld 공식 구현
hitachi-nlp/fld-corpus

Tasks

Formal LogicLogical ReasoningMath

Similar Papers 제목 키워드 기반

Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data

2024-09-19 · Jiaming Zhou, Abbas Ghaddar, Ge Zhang, Liheng Ma 외

Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains. In this wor…

Logical ReasoningSpatial Reasoning

Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning

2025-06-26 · Xin Xu, Tianhao Chen, Fan Zhang, Wanlong Liu 외

While slow-thinking large language models (LLMs) exhibit reflection-like reasoning, commonly referred to as the "aha moment:, their ability to generate informative critiques and refine prior solutions remains limited. In…

SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction

2025-09-29 · Lawrence Phillips, Marc Boubnovski Martell, Aditya Misra, Josefa Lia Stoisser 외 arxiv

Predicting cellular responses to genetic perturbations represents a fundamental challenge in systems biology, critical for advancing therapeutic discovery and virtual cell modeling. While large language models (LLMs) sho…

A Survey on Large Language Models for Mathematical Reasoning

2025-06-10 · Peng-Yuan Wang, Tian-Shuo Liu, Chenyang Wang, Yi-Di Wang 외

Mathematical reasoning has long represented one of the most fundamental and challenging frontiers in artificial intelligence research. In recent years, large language models (LLMs) have achieved significant advances in t…

Answer GenerationMathematical ReasoningSurvey

ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning

2024-12-04 · Zhe Xie, Zeyan Li, Xiao He, Longlong Xu 외

Understanding time series is crucial for its application in real-world scenarios. Recently, large language models (LLMs) have been increasingly applied to time series tasks, leveraging their strong language capabilities …

AttributeTime SeriesTime Series Analysis