paper-with-me

홈 › Papers

ChemCrow: Augmenting large-language models with chemistry tools

2023-04-11 · Andres M Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, Philippe Schwaller

Over the last decades, excellent computational chemistry tools have been developed. Integrating them into a single platform with enhanced accessibility could help reaching their full potential by overcoming steep learning curves. Recently, large-language models (LLMs) have shown strong performance in tasks across domains, but struggle with chemistry-related problems. Moreover, these models lack access to external knowledge sources, limiting their usefulness in scientific applications. In this study, we introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery, and materials design. By integrating 18 expert-designed tools, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent, three organocatalysts, and guided the discovery of a novel chromophore. Our evaluation, including both LLM and expert assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks. Surprisingly, we find that GPT-4 as an evaluator cannot distinguish between clearly wrong GPT-4 completions and Chemcrow's performance. Our work not only aids expert chemists and lowers barriers for non-experts, but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.

📄 PDF Abstract BibTeX arXiv:2304.05376

Code (3)

ur-whitelab/chemcrow-public 공식 구현
ur-whitelab/chemcrow-runs 공식 구현
whitead/synspace 공식 구현

Tasks

Computational chemistryDrug Discovery

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 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 $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving

2024-11-11 · Botao Yu, Frazier N. Baker, Ziru Chen, Garrett Herb 외

To enhance large language models (LLMs) for chemistry problem solving, several LLM-based agents augmented with tools have been proposed, such as ChemCrow and Coscientist. However, their evaluations are narrow in scope, l…

Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery

2025-07-09 · Malikussaid, Hilal Hudan Nuha, Isman Kurniawan arxiv

Large Language Models frequently generate outputs that appear scientifically reasonable yet violate fundamental principles--a phenomenon we characterize as the "plausibility-validity gap." This challenge proves especiall…

ChemHAS: Hierarchical Agent Stacking for Enhancing Chemistry Tools

2025-05-27 · Zhucong Li, Bowei Zhang, Jin Xiao, Zhijian Zhou 외

Large Language Model (LLM)-based agents have demonstrated the ability to improve performance in chemistry-related tasks by selecting appropriate tools. However, their effectiveness remains limited by the inherent predict…

AI AgentLanguage ModelingLanguage ModellingLarge Language Model+1

The Tokenization Bottleneck: How Vocabulary Extension Improves Chemistry Representation Learning in Pretrained Language Models

2025-11-18 · Prathamesh Kalamkar, Ned Letcher, Meissane Chami, Sahger Lad 외 arxiv

The application of large language models (LLMs) to chemistry is frequently hampered by a "tokenization bottleneck", where tokenizers tuned on general-domain text tend to fragment chemical representations such as SMILES i…

Representation Learning

From Generalist to Specialist: A Survey of Large Language Models for Chemistry

2024-12-28 · Yang Han, Ziping Wan, Lu Chen, Kai Yu 외

Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP). However, the predominant pretraining of LLMs on extensive web-based texts re…

scientific discoverySurvey