Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.00821 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929609645228032 |
|---|---|
| author | Jaiswal, Raj Jain, Dhruv Popat, Harsh Parimal Anand, Avinash Dharmadhikari, Abhishek Marathe, Atharva Shah, Rajiv Ratn |
| author_facet | Jaiswal, Raj Jain, Dhruv Popat, Harsh Parimal Anand, Avinash Dharmadhikari, Abhishek Marathe, Atharva Shah, Rajiv Ratn |
| contents | Large Language Models (LLMs) demonstrate remarkable capabilities in various reasoning tasks. However, they encounter significant challenges when it comes to scientific reasoning, particularly in physics, which requires not only mathematical reasoning but also factual and conceptual understanding. When addressing complex physics problems, LLMs typically face three key issues: problem miscomprehension, incorrect concept application, and computational errors. While each of these problems can be addressed individually, there is a need for a generalized approach that can tackle all three issues simultaneously. To address this, we introduce Mixture of Refinement Agents (MoRA), a novel agentic refinement framework that iteratively refines the LLM generated base solution by correcting the aforementioned errors, resulting in a significant performance improvement for open-source LLMs. Our approach aims to bridge the gap between opensource LLMs and GPT-4o by utilizing the latter as error identifier to guide these refinement agents. We evaluate our approach on the SciEval and MMLU subsets along with our own physics dataset (PhysicsQA). MoRA significantly improves the performance of Llama-3-70B and Gemma-2-27B on these datasets, achieving up to a 16% increase in final answer accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00821 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents Jaiswal, Raj Jain, Dhruv Popat, Harsh Parimal Anand, Avinash Dharmadhikari, Abhishek Marathe, Atharva Shah, Rajiv Ratn Artificial Intelligence Large Language Models (LLMs) demonstrate remarkable capabilities in various reasoning tasks. However, they encounter significant challenges when it comes to scientific reasoning, particularly in physics, which requires not only mathematical reasoning but also factual and conceptual understanding. When addressing complex physics problems, LLMs typically face three key issues: problem miscomprehension, incorrect concept application, and computational errors. While each of these problems can be addressed individually, there is a need for a generalized approach that can tackle all three issues simultaneously. To address this, we introduce Mixture of Refinement Agents (MoRA), a novel agentic refinement framework that iteratively refines the LLM generated base solution by correcting the aforementioned errors, resulting in a significant performance improvement for open-source LLMs. Our approach aims to bridge the gap between opensource LLMs and GPT-4o by utilizing the latter as error identifier to guide these refinement agents. We evaluate our approach on the SciEval and MMLU subsets along with our own physics dataset (PhysicsQA). MoRA significantly improves the performance of Llama-3-70B and Gemma-2-27B on these datasets, achieving up to a 16% increase in final answer accuracy. |
| title | Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2412.00821 |