Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments

• URL: http://arxiv.org/abs/2502.17956v1
• Date: Tue, 25 Feb 2025 08:27:28 GMT
• Title: Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
• Abstract summary: Multi-step reasoning is essential for large language models (LLMs), yet multilingual performance remains challenging.<n>While Chain-of-Thought (CoT) prompting improves reasoning, it struggles with non-English languages due to the entanglement of reasoning and execution.<n>We propose a framework to evaluate Program-of-Thought (PoT) prompting, offering a promising alternative but shifting the challenge to generating programs from non-English questions.
• Score: 38.191619790402655
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-step reasoning is essential for large language models (LLMs), yet multilingual performance remains challenging. While Chain-of-Thought (CoT) prompting improves reasoning, it struggles with non-English languages due to the entanglement of reasoning and execution. Program-of-Thought (PoT) prompting separates reasoning from execution, offering a promising alternative but shifting the challenge to generating programs from non-English questions. We propose a framework to evaluate PoT by separating multilingual reasoning from code execution to examine (i) the impact of fine-tuning on question-reasoning alignment and (ii) how reasoning quality affects answer correctness. Our findings demonstrate that PoT fine-tuning substantially enhances multilingual reasoning, outperforming CoT fine-tuned models. We further demonstrate a strong correlation between reasoning quality (measured through code quality) and answer accuracy, highlighting its potential as a test-time performance improvement heuristic.

Related papers

• LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance [77.58408743830314]
  Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models.<n>But its benefits have not fully translated to multilingual contexts.<n>We develop a novel framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks.
  arXiv  Detail & Related papers  (2026-05-21T14:47:52Z)
• Align to the Pivot: Dual Alignment with Self-Feedback for Multilingual Math Reasoning [71.4175109189942]
  We present Pivot-Aligned Self-Feedback Multilingual Reasoning (PASMR)<n>This approach designates the model's primary language as the pivot language.<n>It establishes a cross-lingual self-feedback mechanism without relying on external correct answers or reward models.
  arXiv  Detail & Related papers  (2026-01-25T03:20:00Z)
• A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages [48.68444770923683]
  We present the first comprehensive study of multilingual Chain-of-Thought (CoT) reasoning.<n>We measure language compliance, answer accuracy, and answer consistency when LRMs are prompt-hacked to think in a target language.<n>We find that the quality and effectiveness of thinking traces vary substantially depending on the prompt language.
  arXiv  Detail & Related papers  (2025-10-10T17:06:50Z)
• Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning [85.7304930030649]
  We propose M-Thinker, which is trained by a Language Consistency reward and a Cross-lingual Thinking Alignment reward.<n>M-Thinker achieves nearly 100% language consistency and superior performance on two multilingual benchmarks.
  arXiv  Detail & Related papers  (2025-10-08T17:55:02Z)
• Long Chain-of-Thought Reasoning Across Languages [14.79632337642471]
  We investigate four key stages of model development: scaling, pretraining, post-training, and inference.<n>We find that scaling reasoning model size improves multilingual task performance in En-CoT, but Target-CoT performance lags behind.<n>Given the scarcity of high-quality reasoning traces in languages other than English, we explore synthetic data curation approaches for post-training.
  arXiv  Detail & Related papers  (2025-08-20T16:22:51Z)
• Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? [59.970391602080205]
  Despite multilingual training, LRMs tend to default to reasoning in high-resource languages at test time.<n>Cultural reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior.
  arXiv  Detail & Related papers  (2025-05-23T02:46:18Z)
• When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners [111.50503126693444]
  We show that language-specific ablation consistently boosts multilingual reasoning performance.<n>Compared to post-training, our training-free ablation achieves comparable or superior results with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-05-21T08:35:05Z)
• Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique [66.94905631175209]
  We propose a novel inference-time scaling approach -- stepwise natural language self-critique (PANEL) It employs self-generated natural language critiques as feedback to guide the step-level search process. This approach bypasses the need for task-specific verifiers and the associated training overhead.
  arXiv  Detail & Related papers  (2025-03-21T17:59:55Z)
• Demystifying Multilingual Chain-of-Thought in Process Reward Modeling [71.12193680015622]
  We tackle the challenge of extending process reward models (PRMs) to multilingual settings.<n>We train multilingual PRMs on a dataset spanning seven languages, which is translated from English.<n>Our results highlight the sensitivity of multilingual PRMs to both the number of training languages and the volume of English data.
  arXiv  Detail & Related papers  (2025-02-18T09:11:44Z)
• AdaCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Chain-of-Thought [19.692743208974296]
  We introduce AdaCoT (Adaptive Chain-of-Thought), a framework that enhances multilingual reasoning.<n>AdaCoT dynamically routing thought processes through intermediary "thinking languages" before generating target-language responses.
  arXiv  Detail & Related papers  (2025-01-27T15:48:57Z)
• Reasoning Elicitation in Language Models via Counterfactual Feedback [17.908819732623716]
  We derive novel metrics that balance accuracy in factual and counterfactual questions. We propose several fine-tuning approaches that aim to elicit better reasoning mechanisms. We evaluate the performance of the fine-tuned language models in a variety of realistic scenarios.
  arXiv  Detail & Related papers  (2024-10-02T15:33:30Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• Enhancing Chain of Thought Prompting in Large Language Models via Reasoning Patterns [26.641713417293538]
  Chain of Thought (CoT) prompting can encourage language models to engage in logical reasoning. We propose leveraging reasoning patterns to enhance CoT prompting effectiveness.
  arXiv  Detail & Related papers  (2024-04-23T07:50:00Z)
• MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization [65.31411639849516]
  We propose a Multilingual-Alignment-as-Preference Optimization framework (MAPO) to align the reasoning processes in other languages with the dominant language. Specifically, we harness an off-the-shelf translation model for the consistency between answers in non-dominant and dominant languages. Experiments show that MAPO stably achieves significant improvements in the multilingual reasoning of various models.
  arXiv  Detail & Related papers  (2024-01-12T18:03:54Z)
• Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts [1.8175282137722093]
  Chain-of-Thought (CoT) methods empower Large Language Models (LLMs) to solve complex tasks in a step-by-step manner. The ability to deliver multi-step reasoning remains limited to English because of the imbalance in the distribution of pre-training data. We propose Cross-lingual Tree-of-Thoughts (Cross-ToT), a method for aligning Cross-lingual CoT reasoning across languages.
  arXiv  Detail & Related papers  (2023-11-14T11:49:43Z)
• Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages [46.496557448392494]
  Chain-of-thought (CoT) is capable of eliciting models to explicitly generate reasoning paths. Existing zero-shot prompting techniques are limited to a single language. We introduce cross-lingual prompting (CLP), aiming to improve zero-shot CoT reasoning across languages.
  arXiv  Detail & Related papers  (2023-10-23T10:56:03Z)
• Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement [50.62461749446111]
  Self-Polish (SP) is a novel method that facilitates the model's reasoning by guiding it to progressively refine the given problems to be more comprehensible and solvable. SP is to all other prompting methods of answer/reasoning side like CoT, allowing for seamless integration with state-of-the-art techniques for further improvement.
  arXiv  Detail & Related papers  (2023-05-23T19:58:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.