Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.07980 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913686645374976 |
|---|---|
| author | Skelic, Lejla Xu, Yan Cox, Matthew Lu, Wenjie Yu, Tao Han, Ruonan |
| author_facet | Skelic, Lejla Xu, Yan Cox, Matthew Lu, Wenjie Yu, Tao Han, Ruonan |
| contents | The role of Large Language Models (LLMs) has not been extensively explored in analog circuit design, which could benefit from a reasoning-based approach that transcends traditional optimization techniques. In particular, despite their growing relevance, there are no benchmarks to assess LLMs' reasoning capability about circuits. Therefore, we created the CIRCUIT dataset consisting of 510 question-answer pairs spanning various levels of analog-circuit-related subjects. The best-performing model on our dataset, GPT-4o, achieves 48.04% accuracy when evaluated on the final numerical answer. To evaluate the robustness of LLMs on our dataset, we introduced a unique feature that enables unit-test-like evaluation by grouping questions into unit tests. In this case, GPT-4o can only pass 27.45% of the unit tests, highlighting that the most advanced LLMs still struggle with understanding circuits, which requires multi-level reasoning, particularly when involving circuit topologies. This circuit-specific benchmark highlights LLMs' limitations, offering valuable insights for advancing their application in analog integrated circuit design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07980 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs Skelic, Lejla Xu, Yan Cox, Matthew Lu, Wenjie Yu, Tao Han, Ruonan Machine Learning Artificial Intelligence The role of Large Language Models (LLMs) has not been extensively explored in analog circuit design, which could benefit from a reasoning-based approach that transcends traditional optimization techniques. In particular, despite their growing relevance, there are no benchmarks to assess LLMs' reasoning capability about circuits. Therefore, we created the CIRCUIT dataset consisting of 510 question-answer pairs spanning various levels of analog-circuit-related subjects. The best-performing model on our dataset, GPT-4o, achieves 48.04% accuracy when evaluated on the final numerical answer. To evaluate the robustness of LLMs on our dataset, we introduced a unique feature that enables unit-test-like evaluation by grouping questions into unit tests. In this case, GPT-4o can only pass 27.45% of the unit tests, highlighting that the most advanced LLMs still struggle with understanding circuits, which requires multi-level reasoning, particularly when involving circuit topologies. This circuit-specific benchmark highlights LLMs' limitations, offering valuable insights for advancing their application in analog integrated circuit design. |
| title | CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.07980 |