paper-with-me

홈 › Papers

Pensez: Less Data, Better Reasoning -- Rethinking French LLM

2025-03-17 · Huy Hoang Ha

Large language models (LLMs) have demonstrated remarkable capabilities in various natural language processing tasks. However, achieving strong performance in specialized domains like mathematical reasoning and non-English languages often requires extensive training on massive datasets. This paper investigates a contrasting approach: strategic fine-tuning on a small, high-quality, bilingual (English-French) dataset to enhance both the reasoning capabilities and French language proficiency of a large language model. Rather than relying on scale, we explore the hypothesis that targeted data curation and optimized training can achieve competitive, or even superior, performance. We demonstrate, through targeted supervised fine-tuning (SFT) on only 2,000 carefully selected samples, significant improvements in mathematical reasoning. Specifically, Pensez 7B exhibits an increase in accuracy of the base model up to 20% on the AIME25 and a 12% increase on a French MATH level 5 benchmark. These results challenge the prevailing assumption that massive datasets are aprerequisite for strong reasoning performance in LLMs, highlighting the potential of strategic data curation and optimized fine-tuning for enhancing both specialized skills and multilingual capabilities. Our findings have implications for the efficient development of high-performing, multilingual LLMs, especially in resource-constrained scenarios.

📄 PDF Abstract BibTeX arXiv:2503.13661

Code (0)

등록된 구현이 없습니다.

Tasks

Large Language ModelMathMathematical Reasoning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Inference-Time Rethinking with Latent Thought Vectors for Math Reasoning

2026-02-06 · Deqian Kong, Minglu Zhao, Aoyang Qin, Bo Pang 외 arxiv

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a gene…

Mathematical Reasoning

Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning

2025-05-23 · Michael Hassid, Gabriel Synnaeve, Yossi Adi, Roy Schwartz

Reasoning large language models (LLMs) heavily rely on scaling test-time compute to perform complex reasoning tasks by generating extensive "thinking" chains. While demonstrating impressive results, this approach incurs …

ATM: Action Temporality Modeling for Video Question Answering

2023-09-05 · Junwen Chen, Jie Zhu, Yu Kong

Despite significant progress in video question answering (VideoQA), existing methods fall short of questions that require causal/temporal reasoning across frames. This can be attributed to imprecise motion representation…

Contrastive LearningOptical Flow EstimationQuestion AnsweringVideo Question Answering

Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?

2024-02-28 · Qineng Wang, ZiHao Wang, Ying Su, Hanghang Tong 외

Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic experiments, where we propose a novel group disc…

Rethinking Dialogue State Tracking with Reasoning

2020-05-27 · Lizi Liao, Yunshan Ma, Wenqiang Lei, Tat-Seng Chua

Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a…

Dialogue ManagementDialogue State TrackingManagement