paper-with-me

홈 › Papers

Structured Chemistry Reasoning with Large Language Models

2023-11-16 · Siru Ouyang, Zhuosheng Zhang, Bing Yan, Xuan Liu, Yejin Choi, Jiawei Han, Lianhui Qin

Large Language Models (LLMs) excel in diverse areas, yet struggle with complex scientific reasoning, especially in the field of chemistry. Different from the simple chemistry tasks (e.g., molecule classification) addressed in previous studies, complex chemistry problems require not only vast knowledge and precise calculation, but also compositional reasoning about rich dynamic interactions of different concepts (e.g., temperature changes). Our study shows that even advanced LLMs, like GPT-4, can fail easily in different ways. Interestingly, the errors often stem not from a lack of domain knowledge within the LLMs, but rather from the absence of an effective reasoning structure that guides the LLMs to elicit the right knowledge, incorporate the knowledge in step-by-step reasoning, and iteratively refine results for further improved quality. On this basis, we introduce StructChem, a simple yet effective prompting strategy that offers the desired guidance and substantially boosts the LLMs' chemical reasoning capability. Testing across four chemistry areas -- quantum chemistry, mechanics, physical chemistry, and kinetics -- StructChem substantially enhances GPT-4's performance, with up to 30\% peak improvement. Our analysis also underscores the unique difficulties of precise grounded reasoning in science with LLMs, highlighting a need for more research in this area. Code is available at \url{https://github.com/ozyyshr/StructChem}.

📄 PDF Abstract BibTeX arXiv:2311.09656

Code (1)

ozyyshr/structchem 공식 구현 pytorch

Tasks

General Knowledge

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

QCBench: Evaluating Large Language Models on Domain-Specific Quantitative Chemistry

2025-08-03 · Jiaqing Xie, Weida Wang, Ben Gao, Zhuo Yang 외 arxiv

Quantitative chemistry is central to modern chemical research, yet the ability of large language models (LLMs) to perform its rigorous, step-by-step calculations remains underexplored. To fill this blank, we propose QCBe…

Mathematical Reasoning

Evaluating Large Language Models on Multimodal Chemistry Olympiad Exams

2025-12-17 · Yiming Cui, Xin Yao, Yuxuan Qin, Xin Li 외 arxiv

Multimodal scientific reasoning remains a significant challenge for large language models (LLMs), particularly in chemistry, where problem-solving relies on symbolic diagrams, molecular structures, and structured visual …

Visual Grounding

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models

2026-06-02 · Hongyu Guo, Hao Li, He Cao, Gongbo Zhang 외 arxiv

Large language models are increasingly used as chemistry assistants, yet most chemistry benchmarks still score only final answers. This masks a critical failure mode: a model may output the correct molecule, product, or …

Rethinking Molecular Text Representations for LLMs: An Empirical Study

2026-06-02 · Arun Raja, Garrett M. Morris, Kian Ming A. Chai arxiv

Large language models (LLMs) are increasingly used for molecular tasks, but it remains unclear which molecular representation to use. We present a systematic benchmark evaluating LLM molecular competence across nine repr…

ChemPro: A Progressive Chemistry Benchmark for Large Language Models

2026-02-03 · Aaditya Baranwal, Shruti Vyas arxiv

We introduce ChemPro, a progressive benchmark with 4100 natural language question-answer pairs in Chemistry, across 4 coherent sections of difficulty designed to assess the proficiency of Large Language Models (LLMs) in …