paper-with-me

Papers

Demystifying Multilingual Chain-of-Thought in Process Reward Modeling

2025-02-18 · Weixuan Wang, Minghao Wu, Barry Haddow, Alexandra Birch

Large language models (LLMs) are designed to perform a wide range of tasks. To improve their ability to solve complex problems requiring multi-step reasoning, recent research leverages process reward modeling to provide fine-grained feedback at each step of the reasoning process for reinforcement learning (RL), but it predominantly focuses on English. In this paper, we tackle the critical challenge of extending process reward models (PRMs) to multilingual settings. To achieve this, we train multilingual PRMs on a dataset spanning seven languages, which is translated from English. Through comprehensive evaluations on two widely used reasoning benchmarks across 11 languages, we demonstrate that multilingual PRMs not only improve average accuracy but also reduce early-stage reasoning errors. Furthermore, our results highlight the sensitivity of multilingual PRMs to both the number of training languages and the volume of English data, while also uncovering the benefits arising from more candidate responses and trainable parameters. This work opens promising avenues for robust multilingual applications in complex, multi-step reasoning tasks. In addition, we release the code to foster research along this line.

📄 PDF Abstract BibTeX arXiv:2502.12663

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

AdaCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Chain-of-Thought

2025-01-27 · Xin Huang, Tarun Kumar Vangani, Zhengyuan Liu, Bowei Zou 외

Large language models have shown impressive multilingual capabilities through pretraining on diverse corpora. While these models show strong reasoning abilities, their performance varies significantly across languages du…

Machine Translation

Demystifying Long Chain-of-Thought Reasoning in LLMs

2025-02-05 · Edward Yeo, Yuxuan Tong, Morry Niu, Graham Neubig 외

Scaling inference compute enhances reasoning in large language models (LLMs), with long chains-of-thought (CoTs) enabling strategies like backtracking and error correction. Reinforcement learning (RL) has emerged as a cr…

Reinforcement Learning (RL)

Demystifying Entropy-based Selection for Chain-of-Thought Compression in Large Reasoning Models

2026-07-30 · Sara Candussio, Daniel Scalena, Luca Bortolussi, Elisabetta Fersini 외 arxiv

Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (CoT) reasoning with negligible accuracy loss. We test the robustness of low- and high-entropy CoT step selection methods ac…

Language Models are Multilingual Chain-of-Thought Reasoners

2022-10-06 · Freda Shi, Mirac Suzgun, Markus Freitag, Xuezhi Wang 외

We evaluate the reasoning abilities of large language models in multilingual settings. We introduce the Multilingual Grade School Math (MGSM) benchmark, by manually translating 250 grade-school math problems from the GSM…

GSM8KMath

TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes

2023-11-17 · Bibek Upadhayay, Vahid Behzadan

Creating multilingual LLMs poses a significant challenge. Pretraining or fine-tuning LLMs to adopt new languages is evidently very costly. Furthermore, there exist limitations concerning benchmark datasets and the metric…

Cross-Lingual TransferTranslation