Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

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

Domaine:

natural language processing

Type de record:

papermodel
Créateur:
ZheHuang, XinLiuVan
Hôte:avatar
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. AAAI 2026

Visit

arxiv.org

Tags

Computation and LanguageArtificial Intelligence

Similaires

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning FrameworkTaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought ProcessesLanguage Models are Multilingual Chain-of-Thought ReasonersRethinking the Multilingual Reasoning Gap with Layer SwapOptimal Transport Distillation for Zero-Shot Cross-Lingual Reasoning in Multilingual LLMsRethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs

Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework

Cross-lingual chain-of-thought (XCoT) with self-consistency markedly enhances multilingual reasoning

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

Creating multilingual LLMs poses a significant challenge. Pretraining or fine-tuning LLMs to adopt n

Language Models are Multilingual Chain-of-Thought Reasoners

We evaluate the reasoning abilities of large language models in multilingual settings. We introduce

Rethinking the Multilingual Reasoning Gap with Layer Swap

Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, ev

Optimal Transport Distillation for Zero-Shot Cross-Lingual Reasoning in Multilingual LLMs

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi

Rethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs

Cross-lingual alignment (CLA) aims to align multilingual representations, enabling Large Language Mo