paper-with-me

홈 › Papers

Logic Contrastive Reasoning with Lightweight Large Language Model for Math Word Problems

2024-08-29 · Ding Kai, Ma Zhenguo, Yan Xiaoran

This study focuses on improving the performance of lightweight Large Language Models (LLMs) in mathematical reasoning tasks. We introduce a novel method for measuring mathematical logic similarity and design an automatic screening mechanism to construct a set of reference problems that integrate both semantic and logical similarity. By employing carefully crafted positive and negative example prompts, we guide the model towards adopting sound reasoning logic. To the best of our knowledge, this is the first attempt to utilize retrieval-enhanced generation for mathematical problem-solving. Experimental results demonstrate that our method achieves a 15.8% improvement over the Chain of Thought approach on the SVAMP dataset and a 21.5 % improvement on the GSM8K dataset. Further application of this method to a large-scale model with 175 billion parameters yields performance comparable to the best results on both aforementioned datasets. Finally, we conduct an analysis of errors during the reasoning process, providing valuable insights and directions for future research on reasoning tasks using large language models.

📄 PDF Abstract BibTeX arXiv:2409.00131

Code (0)

등록된 구현이 없습니다.

Tasks

GSM8KLanguage ModelingLanguage ModellingLarge Language ModelMathMathematical Problem-SolvingMathematical Reasoning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Can You Tell the Difference? Contrastive Explanations for ABox Entailments

2025-11-14 · Patrick Koopmann, Yasir Mahmood, Axel-Cyrille Ngonga Ngomo, Balram Tiwari arxiv

We introduce the notion of contrastive ABox explanations to answer questions of the type "Why is a an instance of C, but b is not?". While there are various approaches for explaining positive entailments (why is C(a) ent…

Are LLMs Rigorous Logical Reasoner? Empowering Natural Language Proof Generation with Contrastive Stepwise Decoding

2023-11-12 · Ying Su, Xiaojin Fu, Mingwen Liu, Zhijiang Guo

Logical reasoning remains a pivotal component within the realm of artificial intelligence. The recent evolution of large language models (LLMs) has marked significant progress in this domain. The adoption of strategies l…

Language ModelingLanguage ModellingLogical ReasoningNavigate

Analogical Structure, Minimal Contextual Cues and Contrastive Distractors: Input Design for Sample-Efficient Linguistic Rule Induction

2025-11-13 · Chunyang Jiang, Paola Merlo arxiv

Large language models achieve strong performance on many tasks, but their training makes it hard to see which properties of the input support efficient linguistic rule learning. We ask how three cognitively-inspired prin…

Contrastive LearningSentence Completion

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning

2026-01-24 · Lianlei Shan, Han Chen, Yixuan Wang, Zhenjie Liu 외 arxiv

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather tha…

Reinforcement LearningContrastive LearningText Generation

Contrastive Chain-of-Thought Prompting

2023-11-15 · Yew Ken Chia, Guizhen Chen, Luu Anh Tuan, Soujanya Poria 외

Despite the success of chain of thought in enhancing language model reasoning, the underlying process remains less well understood. Although logically sound reasoning appears inherently crucial for chain of thought, prio…

Language ModelingLanguage Modellingvalid