Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study
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_ | 1866915431424458752 |
|---|---|
| author | Khodadad, Mohammad Kasmaee, Ali Shiraee Astaraki, Mahdi Sherck, Nicholas Mahyar, Hamidreza Samiee, Soheila |
| author_facet | Khodadad, Mohammad Kasmaee, Ali Shiraee Astaraki, Mahdi Sherck, Nicholas Mahyar, Hamidreza Samiee, Soheila |
| contents | In this study, we introduced a new benchmark consisting of a curated dataset and a defined evaluation process to assess the compositional reasoning capabilities of large language models within the chemistry domain. We designed and validated a fully automated pipeline, verified by subject matter experts, to facilitate this task. Our approach integrates OpenAI reasoning models with named entity recognition (NER) systems to extract chemical entities from recent literature, which are then augmented with external knowledge bases to form a comprehensive knowledge graph. By generating multi-hop questions across these graphs, we assess LLM performance in both context-augmented and non-context augmented settings. Our experiments reveal that even state-of-the-art models face significant challenges in multi-hop compositional reasoning. The results reflect the importance of augmenting LLMs with document retrieval, which can have a substantial impact on improving their performance. However, even perfect retrieval accuracy with full context does not eliminate reasoning errors, underscoring the complexity of compositional reasoning. This work not only benchmarks and highlights the limitations of current LLMs but also presents a novel data generation pipeline capable of producing challenging reasoning datasets across various domains. Overall, this research advances our understanding of reasoning in computational linguistics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_16414 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study Khodadad, Mohammad Kasmaee, Ali Shiraee Astaraki, Mahdi Sherck, Nicholas Mahyar, Hamidreza Samiee, Soheila Computation and Language In this study, we introduced a new benchmark consisting of a curated dataset and a defined evaluation process to assess the compositional reasoning capabilities of large language models within the chemistry domain. We designed and validated a fully automated pipeline, verified by subject matter experts, to facilitate this task. Our approach integrates OpenAI reasoning models with named entity recognition (NER) systems to extract chemical entities from recent literature, which are then augmented with external knowledge bases to form a comprehensive knowledge graph. By generating multi-hop questions across these graphs, we assess LLM performance in both context-augmented and non-context augmented settings. Our experiments reveal that even state-of-the-art models face significant challenges in multi-hop compositional reasoning. The results reflect the importance of augmenting LLMs with document retrieval, which can have a substantial impact on improving their performance. However, even perfect retrieval accuracy with full context does not eliminate reasoning errors, underscoring the complexity of compositional reasoning. This work not only benchmarks and highlights the limitations of current LLMs but also presents a novel data generation pipeline capable of producing challenging reasoning datasets across various domains. Overall, this research advances our understanding of reasoning in computational linguistics. |
| title | Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.16414 |