# ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data

arXiv: https://arxiv.org/abs/2506.23520 · HTML: https://mlsanity.com/paper/2506.23520/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Code and instruction data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Code and instruction data synthesis](https://mlsanity.com/synth/code-and-instruction-data-synthesis/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models](https://mlsanity.com/paper/2402.13064/) (2024)
- [Unifying Molecular and Textual Representations via Multi-task Language Modelling](https://mlsanity.com/paper/2301.12586/) (2023)
- [Language acquisition: do children and language models follow similar learning stages?](https://mlsanity.com/paper/2306.03586/) (2023)
- [Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate](https://mlsanity.com/paper/2401.16788/) (2024)
- [Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching](https://mlsanity.com/paper/2303.16756/) (2023)
- [PRE: A Peer Review Based Large Language Model Evaluator](https://mlsanity.com/paper/2401.15641/) (2024)
- [ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining](https://mlsanity.com/paper/2405.14225/) (2024)
- [OpenChemIE: An Information Extraction Toolkit For Chemistry Literature](https://mlsanity.com/paper/2404.01462/) (2024)
- [LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods](https://mlsanity.com/paper/2407.00322/) (2024)
- [UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment](https://mlsanity.com/paper/2404.00044/) (2024)

## Built on by (most cited first, 3 of 3)

- [A Scientific Reasoning Model for Organic Synthesis Procedure Generation](https://mlsanity.com/paper/2512.13668/) (2025)
- [LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory](https://mlsanity.com/paper/2605.02288/) (2026)
- [Molecular LLM Agents: From Architectural Design to Scientific Autonomy](https://mlsanity.com/paper/2608.23104/) (2026)

## Abstract (arXiv)

With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required for developing reliable computer-aided extraction protocols. Here, we present ChemActor, a fully fine-tuned large language model (LLM), as a chemical executor to convert between unstructured experimental procedures and structured action sequences. We propose a sequential LLM-generated data framework to address the challenges of insufficient and low-quality annotated data. This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input. Additionally, we introduce a novel multi-round LLMs circle review metric, which reflects the model's advanced understanding of chemical experimental procedures. Extensive experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor, augmented by LLM-generated data, achieves state-of-the-art performance, outperforming the baseline model by 10%. The code is available at: https://github.com/Zhanghahah/ChemActor.