Thinking in Many Modes: How Composite Reasoning Elevates Large Language Model Performance with Limited Data
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914058140123136 |
|---|---|
| author | Ahmad, Zishan Gopalakrishnan, Saisubramaniam |
| author_facet | Ahmad, Zishan Gopalakrishnan, Saisubramaniam |
| contents | Large Language Models (LLMs), despite their remarkable capabilities, rely on singular, pre-dominant reasoning paradigms, hindering their performance on intricate problems that demand diverse cognitive strategies. To address this, we introduce Composite Reasoning (CR), a novel reasoning approach empowering LLMs to dynamically explore and combine multiple reasoning styles like deductive, inductive, and abductive for more nuanced problem-solving. Evaluated on scientific and medical question-answering benchmarks, our approach outperforms existing baselines like Chain-of-Thought (CoT) and also surpasses the accuracy of DeepSeek-R1 style reasoning (SR) capabilities, while demonstrating superior sample efficiency and adequate token usage. Notably, CR adaptively emphasizes domain-appropriate reasoning styles. It prioritizes abductive and deductive reasoning for medical question answering, but shifts to causal, deductive, and inductive methods for scientific reasoning. Our findings highlight that by cultivating internal reasoning style diversity, LLMs acquire more robust, adaptive, and efficient problem-solving abilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22224 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Thinking in Many Modes: How Composite Reasoning Elevates Large Language Model Performance with Limited Data Ahmad, Zishan Gopalakrishnan, Saisubramaniam Computation and Language Artificial Intelligence Large Language Models (LLMs), despite their remarkable capabilities, rely on singular, pre-dominant reasoning paradigms, hindering their performance on intricate problems that demand diverse cognitive strategies. To address this, we introduce Composite Reasoning (CR), a novel reasoning approach empowering LLMs to dynamically explore and combine multiple reasoning styles like deductive, inductive, and abductive for more nuanced problem-solving. Evaluated on scientific and medical question-answering benchmarks, our approach outperforms existing baselines like Chain-of-Thought (CoT) and also surpasses the accuracy of DeepSeek-R1 style reasoning (SR) capabilities, while demonstrating superior sample efficiency and adequate token usage. Notably, CR adaptively emphasizes domain-appropriate reasoning styles. It prioritizes abductive and deductive reasoning for medical question answering, but shifts to causal, deductive, and inductive methods for scientific reasoning. Our findings highlight that by cultivating internal reasoning style diversity, LLMs acquire more robust, adaptive, and efficient problem-solving abilities. |
| title | Thinking in Many Modes: How Composite Reasoning Elevates Large Language Model Performance with Limited Data |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.22224 |