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

[2501.16154] AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2501.16154 (cs) [Submitted on 27 Jan 2025 ( v1 ), last revised 14 Apr 2026 (this version, v4)] Title: AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought Authors: Weihua Zheng , Xin Huang , Zhengyuan Liu , Tarun Kumar Vangani , Bowei Zou , Xiyan Tao , Yuhao Wu , Ai Ti Aw , Nancy F. Chen , Roy Ka-Wei Lee View a PDF of the paper titled AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought, by Weihua Zheng and 9 other authors View PDF HTML (experimental) Abstract: Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. Although these models show strong reasoning abilities, their performance varies significantly between languages due to the imbalanced distribution of training data. Existing approaches using sample-level translation for extensive multilingual pretraining and cross-lingual tuning face scalability challenges and often fail to capture nuanced reasoning processes across languages. In this paper, we introduce AdaMCOT (Adaptive Multilingual Chain-of-Thought), a framework that enhances multilingual factual reasoning by dynamically routing thought processes in intermediary "thinking languages" before generating target-language responses. AdaMCOT leverages a language-agnostic core and incorporates an adaptive, reward-based mechanism for selecting optimal reasoning pathways without requiring additional pretraining. Our comprehensive evaluation across multiple benchmarks demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency, with particularly strong performance gains in low-resource language settings. An in-depth analysis of the model's hidden states and semantic space further elucidates the underlying mechanism of our method. The results suggest that adaptive reasoning paths can effectively bridge the performance gap between high and low-resource languages while maintaining cultural and linguistic nuances. Comments: AAAI 2026 Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2501.16154 [cs.CL] (or arXiv:2501.16154v4 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2501.16154 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhengyuan Liu [ view email ] [v1] Mon, 27 Jan 2025 15:48:57 UTC (340 KB) [v2] Fri, 9 May 2025 05:50:14 UTC (336 KB) [v3] Tue, 5 Aug 2025 15:13:54 UTC (1,562 KB) [v4] Tue, 14 Apr 2026 08:15:35 UTC (1,556 KB) Full-text links: Access Paper: View a PDF of the paper titled AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought, by Weihua Zheng and 9 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2025-01 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach#819377
• Argument Quality Assessment with Large Language Models: A Pairwise Bradley-Terry Approach#809384
• Reasoning with Continuous Latent Diffusion#1141647
• Learn Your Own Thoughts: Abstract Token Curriculum#1014305
• $S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient#1142278