Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916862875402240 |
|---|---|
| author | Rueda, Alice Hassan, Mohammed S. Perivolaris, Argyrios Teferra, Bazen G. Samavi, Reza Rambhatla, Sirisha Wu, Yuqi Zhang, Yanbo Cao, Bo Sharma, Divya Krishnan, Sridhar Bhat, Venkat |
| author_facet | Rueda, Alice Hassan, Mohammed S. Perivolaris, Argyrios Teferra, Bazen G. Samavi, Reza Rambhatla, Sirisha Wu, Yuqi Zhang, Yanbo Cao, Bo Sharma, Divya Krishnan, Sridhar Bhat, Venkat |
| contents | Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their ability to perform complex, multi-step reasoning task-essential for applications in science, medicine, and law-remains an area of active investigation. This paper examines the reasoning capabilities of contemporary LLMs, analyzing their strengths, limitations, and potential for improvement. The study uses prompt engineering techniques on the Graduate-Level GoogleProof Q&A (GPQA) dataset to assess the scientific reasoning of GPT-4o. Five popular prompt engineering techniques and two tailored promptings were tested: baseline direct answer (zero-shot), chain-of-thought (CoT), zero-shot CoT, self-ask, self-consistency, decomposition, and multipath promptings. Our findings indicate that while LLMs exhibit emergent reasoning abilities, they often rely on pattern recognition rather than true logical inference, leading to inconsistencies in complex problem-solving. The results indicated that self-consistency outperformed the other prompt engineering technique with an accuracy of 52.99%, followed by direct answer (52.23%). Zero-shot CoT (50%) outperformed multipath (48.44%), decomposition (47.77%), self-ask (46.88%), and CoT (43.75%). Self-consistency performed the second worst in explaining the answers. Simple techniques such as direct answer, CoT, and zero-shot CoT have the best scientific reasoning. We propose a research agenda aimed at bridging these gaps by integrating structured reasoning frameworks, hybrid AI approaches, and human-in-the-loop methodologies. By critically evaluating the reasoning mechanisms of LLMs, this paper contributes to the ongoing discourse on the future of artificial general intelligence and the development of more robust, trustworthy AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers Rueda, Alice Hassan, Mohammed S. Perivolaris, Argyrios Teferra, Bazen G. Samavi, Reza Rambhatla, Sirisha Wu, Yuqi Zhang, Yanbo Cao, Bo Sharma, Divya Krishnan, Sridhar Bhat, Venkat Artificial Intelligence Large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and problem-solving across various domains. However, their ability to perform complex, multi-step reasoning task-essential for applications in science, medicine, and law-remains an area of active investigation. This paper examines the reasoning capabilities of contemporary LLMs, analyzing their strengths, limitations, and potential for improvement. The study uses prompt engineering techniques on the Graduate-Level GoogleProof Q&A (GPQA) dataset to assess the scientific reasoning of GPT-4o. Five popular prompt engineering techniques and two tailored promptings were tested: baseline direct answer (zero-shot), chain-of-thought (CoT), zero-shot CoT, self-ask, self-consistency, decomposition, and multipath promptings. Our findings indicate that while LLMs exhibit emergent reasoning abilities, they often rely on pattern recognition rather than true logical inference, leading to inconsistencies in complex problem-solving. The results indicated that self-consistency outperformed the other prompt engineering technique with an accuracy of 52.99%, followed by direct answer (52.23%). Zero-shot CoT (50%) outperformed multipath (48.44%), decomposition (47.77%), self-ask (46.88%), and CoT (43.75%). Self-consistency performed the second worst in explaining the answers. Simple techniques such as direct answer, CoT, and zero-shot CoT have the best scientific reasoning. We propose a research agenda aimed at bridging these gaps by integrating structured reasoning frameworks, hybrid AI approaches, and human-in-the-loop methodologies. By critically evaluating the reasoning mechanisms of LLMs, this paper contributes to the ongoing discourse on the future of artificial general intelligence and the development of more robust, trustworthy AI systems. |
| title | Understanding LLM Scientific Reasoning through Promptings and Model's Explanation on the Answers |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2505.01482 |