paper-with-me

Papers

Eliciting Better Multilingual Structured Reasoning from LLMs through Code

2024-03-05 · Bryan Li, Tamer Alkhouli, Daniele Bonadiman, Nikolaos Pappas, Saab Mansour

The development of large language models (LLM) has shown progress on reasoning, though studies have largely considered either English or simple reasoning tasks. To address this, we introduce a multilingual structured reasoning and explanation dataset, termed xSTREET, that covers four tasks across six languages. xSTREET exposes a gap in base LLM performance between English and non-English reasoning tasks. We then propose two methods to remedy this gap, building on the insight that LLMs trained on code are better reasoners. First, at training time, we augment a code dataset with multilingual comments using machine translation while keeping program code as-is. Second, at inference time, we bridge the gap between training and inference by employing a prompt structure that incorporates step-by-step code primitives to derive new facts and find a solution. Our methods show improved multilingual performance on xSTREET, most notably on the scientific commonsense reasoning subtask. Furthermore, the models show no regression on non-reasoning tasks, thus demonstrating our techniques maintain general-purpose abilities.

📄 PDF Abstract BibTeX arXiv:2403.02567

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models

2024-06-04 · Huiyuan Lai, Malvina Nissim

Large language models (LLMs) with Chain-of-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks. As most research mainly focuses on English, with few exp…

Math

First Return, Entropy-Eliciting Explore

2025-07-09 · Tianyu Zheng, Tianshun Xing, Qingshui Gu, Taoran Liang 외 arxiv

Reinforcement Learning from Verifiable Rewards (RLVR) improves the reasoning abilities of Large Language Models (LLMs) but it struggles with unstable exploration. We propose FR3E (First Return, Entropy-Eliciting Explore)…

Reinforcement LearningMathematical Reasoning

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

SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models

2025-10-03 · Rui Qi, Zhibo Man, Yufeng Chen, Fengran Mo 외 arxiv

Recent developments have enabled Large Language Models (LLMs) to engage in complex reasoning tasks through deep thinking. However, the capacity of reasoning has not been successfully transferred to non-high-resource lang…

Can Code-Switched Texts Activate a Knowledge Switch in LLMs? A Case Study on English-Korean Code-Switching

2024-10-24 · Seoyeon Kim, Huiseo Kim, Chanjun Park, Jinyoung Yeo 외

Code-switching (CS), a phenomenon where multilingual speakers alternate between languages in a discourse, can convey subtle cultural and linguistic nuances that can be otherwise lost in translation. Recent state-of-the-a…

Question Answering