Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2501.13299 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910819865853952 |
|---|---|
| author | Kumbhar, Shrinidhi Mishra, Venkatesh Coutinho, Kevin Handa, Divij Iquebal, Ashif Baral, Chitta |
| author_facet | Kumbhar, Shrinidhi Mishra, Venkatesh Coutinho, Kevin Handa, Divij Iquebal, Ashif Baral, Chitta |
| contents | Materials discovery and design are essential for advancing technology across various industries by enabling the development of application-specific materials. Recent research has leveraged Large Language Models (LLMs) to accelerate this process. We explore the potential of LLMs to generate viable hypotheses that, once validated, can expedite materials discovery. Collaborating with materials science experts, we curated a novel dataset from recent journal publications, featuring real-world goals, constraints, and methods for designing real-world applications. Using this dataset, we test LLM-based agents that generate hypotheses for achieving given goals under specific constraints. To assess the relevance and quality of these hypotheses, we propose a novel scalable evaluation metric that emulates the process a materials scientist would use to evaluate a hypothesis critically. Our curated dataset, proposed method, and evaluation framework aim to advance future research in accelerating materials discovery and design with LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13299 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents Kumbhar, Shrinidhi Mishra, Venkatesh Coutinho, Kevin Handa, Divij Iquebal, Ashif Baral, Chitta Computation and Language Materials discovery and design are essential for advancing technology across various industries by enabling the development of application-specific materials. Recent research has leveraged Large Language Models (LLMs) to accelerate this process. We explore the potential of LLMs to generate viable hypotheses that, once validated, can expedite materials discovery. Collaborating with materials science experts, we curated a novel dataset from recent journal publications, featuring real-world goals, constraints, and methods for designing real-world applications. Using this dataset, we test LLM-based agents that generate hypotheses for achieving given goals under specific constraints. To assess the relevance and quality of these hypotheses, we propose a novel scalable evaluation metric that emulates the process a materials scientist would use to evaluate a hypothesis critically. Our curated dataset, proposed method, and evaluation framework aim to advance future research in accelerating materials discovery and design with LLMs. |
| title | Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.13299 |