---
title: "KGRxn-LLM — paper by Liu et al. (2026) · BioNLP 2026"
description: "Existing benchmarks mostly test product generation or fact recall, not mechanistic understanding. 41 references."
authors: ["Weichen Liu", "Qiyao Xue", "Yuyang Wu", "Olexandr Isayev", "Natasa Miskov-Zivanov"]
year: 2026
venue: "BioNLP 2026"
source: "https://aclanthology.org/2026.bionlp-1.22/"
doi: "10.18653/v1/2026.bionlp-1.22"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/liu-2026-kgrxn-llm-knowledge-graph-enhanced/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/liu-2026-kgrxn-llm-knowledge-graph-enhanced/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/) / KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning

# KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning

**Authors:** Weichen Liu, Qiyao Xue, Yuyang Wu, Olexandr Isayev and Natasa Miskov-Zivanov · **Year:** 2026 · **Venue:** [BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/) ([BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.bionlp-1.22/) · [PDF](https://aclanthology.org/2026.bionlp-1.22.pdf) · [DOI 10.18653/v1/2026.bionlp-1.22](https://doi.org/10.18653/v1/2026.bionlp-1.22) · [OpenAlex](https://openalex.org/W7166879169)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
General-purpose LLMs often reason poorly about chemical reactions. They mislabel functional groups, mix up reaction classes and propose products with atoms that have no source in the reactants. Existing benchmarks mostly test product generation or fact recall, not mechanistic understanding. The authors address both gaps with KGRxn-LLM and a new benchmark, KGRxn-Bench.

They took 32,000 USPTO reactions and processed them with RDKit (canonicalization, atom mapping, functional-group detection). An LLM-assisted, expert-checked annotation loop then labelled the data. The result is a knowledge graph with several levels, linking individual compounds and the groups they contain to reaction categories (both their identifiers and their names) and to specific reaction instances. An agent-based retriever pulls relevant evidence from the graph, such as group changes, typical patterns and analogous reactions, and supplies it to the LLM. When no exact match exists, it falls back on similarity search.

Grounding 7–8B models this way strongly improves accuracy on both seen and held-out reactions, and also helps on external chemistry and biology benchmarks. This suggests that structured chemical knowledge reduces hallucination in reaction reasoning.

## Key points
- **Data split:** 30,000 USPTO reactions build the KG and the KG-covered benchmark part, and 2,000 are reserved for a hold-out split. KGRxn-Bench contains 1,200 questions on four tasks: functional group identification, reaction type classification, product prediction and reagent prediction.
- **Annotation and retrieval:** Annotation is iterative human-in-the-loop, with resampling until accuracy reaches at least 90%. For unseen reactions, retrieval falls back to Jaccard similarity over the sets of functional groups consumed and formed.
- **Gains on KGRxn-Bench:**
  - Llama-3.1-8B functional group identification on the KG-covered split rises from 58.82% to 94.12%.
  - Qwen2.5-7B on the hold-out split goes from 67.00% to 92.00%.
- **Gains on external benchmarks:**
  - FGBench interaction queries (Qwen2.5-7B): 39.33% → 49.64%.
  - SciKnowEval biology boolean subset (Llama): 88.24% → 95.76%.
- **Limitations:**
  - Only ten coarse reaction types are used.
  - The graph is modest at about 30K reactions.
  - Testing covered only 7–8B models.
  - Code and benchmark are released on GitHub (pitt-miskov-zivanov-lab).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 539 works · 179,533 citations
- [University of North Carolina at Chapel Hill](https://md.research.elamur.ai/free/en/universities/university-of-north-carolina-at-chapel-hill/) — University, Chapel Hill, United States · 67 works · 16,474 citations
- [University of Pittsburgh](https://md.research.elamur.ai/free/en/universities/university-of-pittsburgh/) — University, Pittsburgh, United States · 59 works · 22,324 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🧮 Computational Theory and Mathematics](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · 252 works · [🧱 Materials Science](https://md.research.elamur.ai/free/en/shelves/materials-science/) · 26 works · [🧱 Materials Chemistry](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/) · 26 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [🕸️ Knowledge graphs & ontologies](https://md.research.elamur.ai/free/en/topics/knowledge-graphs/) · 192 works

## Cite

Cite as: Weichen Liu, Qiyao Xue, Yuyang Wu, Olexandr Isayev and Natasa Miskov-Zivanov. 2026. KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning. BioNLP 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{liu2026kgrxn,
  title = {{KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning}},
  author = {Weichen Liu, Qiyao Xue, Yuyang Wu, Olexandr Isayev and Natasa Miskov-Zivanov},
  booktitle = {BioNLP 2026},
  year = {2026},
  doi = {10.18653/v1/2026.bionlp-1.22},
  url = {https://doi.org/10.18653/v1/2026.bionlp-1.22}
}
```

- [← previous KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge](https://md.research.elamur.ai/free/en/papers/robertson-2026-kghalubench-knowledge-graph-based-hallucination/)
- [next → KinyaProp: Fine-Grained Propaganda Annotation in Kinyarwanda](https://md.research.elamur.ai/free/en/papers/niyigaba-2026-kinyaprop-fine-grained-propaganda-annotation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/34/)

## References

41 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, and Heng Ji. 2022. [Translation between molecules and natural language](https://md.research.elamur.ai/free/en/papers/edwards-2022-translation-between-molecules-natural-language/). arXiv preprint arXiv:2204.11817.
2. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
3. Mattias Akke, Soojung Yang, Jurgis Ruza, Jinyeop Song, Elton Pan, and Rafael Gomez-Bombarelli. 2025. Bayesian optimization for biochemical discovery with llms. [find](https://scholar.google.com/scholar?q=Mattias+Akke%2C+Soojung+Yang%2C+Jurgis+Ruza%2C+Jinyeop+Song%2C+Elton+Pan%2C+and+Rafael+Gomez%2DBombarelli%2E+2025%2E+Bayesian+optimization+for+biochemical+discovery+with+llms%2E)
4. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, and 1 others. 2023. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609.
5. Andres M Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, and Philippe Schwaller. 2023. Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:2304.05376. [find](https://scholar.google.com/scholar?q=Andres+M+Bran%2C+Sam+Cox%2C+Oliver+Schilter%2C+Carlo+Baldassari%2C+Andrew+D+White%2C+and+Philippe+Schwaller%2E+2023%2E+Chemcrow%3A+Augmenting+large%2Dlanguage+models+with+chemistry+tools%2E+arXiv+preprint+arXiv%3A2304%2E0537)
6. Quintina Campbell, Sam Cox, Jorge Medina, Brittany Watterson, and Andrew White. 2025. Mdcrow: Automating molecular dynamics workflows with large language models. Machine Learning: Science and Technology. [find](https://scholar.google.com/scholar?q=Quintina+Campbell%2C+Sam+Cox%2C+Jorge+Medina%2C+Brittany+Watterson%2C+and+Andrew+White%2E+2025%2E+Mdcrow%3A+Automating+molecular+dynamics+workflows+with+large+language+models%2E+Machine+Learning%3A+Science+and+Technolo)
7. Shuan Chen, Ramil Babazade, Taewan Kim, Sunkyu Han, and Yousung Jung. 2024. A large-scale reaction dataset of mechanistic pathways of organic reactions. Scientific Data, 11(1):863. [find](https://scholar.google.com/scholar?q=Shuan+Chen%2C+Ramil+Babazade%2C+Taewan+Kim%2C+Sunkyu+Han%2C+and+Yousung+Jung%2E+2024%2E+A+large%2Dscale+reaction+dataset+of+mechanistic+pathways+of+organic+reactions%2E+Scientific+Data%2C+11%281%29%3A863%2E)
8. Yufan Chen, Ching Ting Leung, Jianwei Sun, Yong Huang, Linyan Li, Hao Chen, and Hanyu Gao. 2025. Towards large-scale chemical reaction image parsing via a multimodal large language model. arXiv preprint arXiv:2503.08156. — [arXiv:2503.08156](https://arxiv.org/abs/2503.08156) [find](https://scholar.google.com/scholar?q=Yufan+Chen%2C+Ching+Ting+Leung%2C+Jianwei+Sun%2C+Yong+Huang%2C+Linyan+Li%2C+Hao+Chen%2C+and+Hanyu+Gao%2E+2025%2E+Towards+large%2Dscale+chemical+reaction+image+parsing+via+a+multimodal+large+language+model%2E+arXiv+prepri)
9. Seyone Chithrananda, Gabriel Grand, and Bharath Ramsundar. 2020. Chemberta: large-scale self-supervised pretraining for molecular property prediction. arXiv preprint arXiv:2010.09885. [find](https://scholar.google.com/scholar?q=Seyone+Chithrananda%2C+Gabriel+Grand%2C+and+Bharath+Ramsundar%2E+2020%2E+Chemberta%3A+large%2Dscale+self%2Dsupervised+pretraining+for+molecular+property+prediction%2E+arXiv+preprint+arXiv%3A2010%2E09885%2E)
10. Connor W Coley, Wengong Jin, Luke Rogers, Timothy F Jamison, Tommi S Jaakkola, William H Green, Regina Barzilay, and Klavs F Jensen. 2019. A graph-convolutional neural network model for the prediction of chemical reactivity. Chemical science, 10(2):370–377. [find](https://scholar.google.com/scholar?q=Connor+W+Coley%2C+Wengong+Jin%2C+Luke+Rogers%2C+Timothy+F+Jamison%2C+Tommi+S+Jaakkola%2C+William+H+Green%2C+Regina+Barzilay%2C+and+Klavs+F+Jensen%2E+2019%2E+A+graph%2Dconvolutional+neural+network+model+for+the+prediction)
11. Dong-Xu Cui, Shi-Yu Long, Yi-Xuan Tang, Yue Zhao, and Qiao Li. 2025. Can reasoning power significantly improve the knowledge of large language models for chemistry?� based on conversations with llms. Journal of Chemical Information and Modeling, 65(18):9516–9527. [find](https://scholar.google.com/scholar?q=Dong%2DXu+Cui%2C+Shi%2DYu+Long%2C+Yi%2DXuan+Tang%2C+Yue+Zhao%2C+and+Qiao+Li%2E+2025%2E+Can+reasoning+power+significantly+improve+the+knowledge+of+large+language+models+for+chemistry%3F%EF%BF%BD+based+on+conversations+with+llms%2E+)
12. Kehua Feng, Xinyi Shen, Weijie Wang, Xiang Zhuang, Yuqi Tang, Qiang Zhang, and Keyan Ding. 2024. [Sciknoweval: Evaluating multi-level scientific knowledge of large language models](https://md.research.elamur.ai/free/en/papers/feng-2024-sciknoweval-evaluating-multi-level-scientific/). arXiv preprint arXiv:2406.09098.
13. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, Haofen Wang, and 1 others. 2023. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). arXiv preprint arXiv:2312.10997, 2(1):32.
14. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Peiyi Wang, Qihao Zhu, Runxin Xu, Ruoyu Zhang, Shirong Ma, Xiao Bi, and 1 others. 2025. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948.
15. Taicheng Guo, Bozhao Nan, Zhenwen Liang, Zhichun Guo, Nitesh Chawla, Olaf Wiest, Xiangliang Zhang, and 1 others. 2023. What can large language models do in chemistry? a comprehensive benchmark on eight tasks. Advances in neural information processing systems, 36:59662–59688. [find](https://scholar.google.com/scholar?q=Taicheng+Guo%2C+Bozhao+Nan%2C+Zhenwen+Liang%2C+Zhichun+Guo%2C+Nitesh+Chawla%2C+Olaf+Wiest%2C+Xiangliang+Zhang%2C+and+1+others%2E+2023%2E+What+can+large+language+models+do+in+chemistry%3F+a+comprehensive+benchmark+on+eigh)
16. Yang Han, Ziping Wan, Lu Chen, Kai Yu, and Xin Chen. 2025. From generalist to specialist: A survey of large language models for chemistry. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1106–1123. [find](https://scholar.google.com/scholar?q=Yang+Han%2C+Ziping+Wan%2C+Lu+Chen%2C+Kai+Yu%2C+and+Xin+Chen%2E+2025%2E+From+generalist+to+specialist%3A+A+survey+of+large+language+models+for+chemistry%2E+In+Proceedings+of+the+31st+International+Conference+on+Comput)
17. Ross Irwin, Spyridon Dimitriadis, Jiazhen He, and Esben Jannik Bjerrum. 2022. Chemformer: a pre-trained transformer for computational chemistry. Machine Learning: Science and Technology, 3(1):015022. [find](https://scholar.google.com/scholar?q=Ross+Irwin%2C+Spyridon+Dimitriadis%2C+Jiazhen+He%2C+and+Esben+Jannik+Bjerrum%2E+2022%2E+Chemformer%3A+a+pre%2Dtrained+transformer+for+computational+chemistry%2E+Machine+Learning%3A+Science+and+Technology%2C+3%281%29%3A015022%2E)
18. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, and 1 others. 2024. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv preprint arXiv:2412.16720.
19. José Jiménez-Luna, Francesca Grisoni, Nils Weskamp, and Gisbert Schneider. 2021. Artificial intelligence in drug discovery: recent advances and future perspectives. Expert opinion on drug discovery, 16(9):949–959. [find](https://scholar.google.com/scholar?q=Jos%C3%A9+Jim%C3%A9nez%2DLuna%2C+Francesca+Grisoni%2C+Nils+Weskamp%2C+and+Gisbert+Schneider%2E+2021%2E+Artificial+intelligence+in+drug+discovery%3A+recent+advances+and+future+perspectives%2E+Expert+opinion+on+drug+discovery%2C+1)
20. Qiao Jin, Yifan Yang, Qingyu Chen, and Zhiyong Lu. 2024. [Genegpt: augmenting large language models with domain tools for improved access to biomedical information](https://md.research.elamur.ai/free/en/papers/jin-2023-genegpt-augmenting-large-language-models/). Bioinformatics, 40(2):btae075.
21. Siddhartha Laghuvarapu, Namkyeong Lee, Chufan Gao, and Jimeng Sun. 2025. Moltextqa: A question-answering dataset and benchmark for evaluating multimodal architectures and llms on molecular structure– text understanding. Journal of Data-centric Machine Learning Research. [find](https://scholar.google.com/scholar?q=Siddhartha+Laghuvarapu%2C+Namkyeong+Lee%2C+Chufan+Gao%2C+and+Jimeng+Sun%2E+2025%2E+Moltextqa%3A+A+question%2Danswering+dataset+and+benchmark+for+evaluating+multimodal+architectures+and+llms+on+molecular+structure%E2%80%93+)
22. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, and 1 others. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
23. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
24. Gonzalo Travieso, Alexandre Benatti, and Luciano da F Costa. 2024. An analytical approach to the jaccard similarity index. arXiv preprint arXiv:2410.16436. — [arXiv:2410.16436](https://arxiv.org/abs/2410.16436) [find](https://scholar.google.com/scholar?q=Gonzalo+Travieso%2C+Alexandre+Benatti%2C+and+Luciano+da+F+Costa%2E+2024%2E+An+analytical+approach+to+the+jaccard+similarity+index%2E+arXiv+preprint+arXiv%3A2410%2E16436%2E+%E2%80%94+%5BarXiv%3A2410%2E16436%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2)
25. Hao Li, He Cao, Bin Feng, Yanjun Shao, Xiangru Tang, Zhiyuan Yan, Li Yuan, Yonghong Tian, and Yu Li. 2025. Beyond chemical qa: Evaluating llm’s chemical reasoning with modular chemical operations. arXiv preprint arXiv:2505.21318. — [arXiv:2505.21318](https://arxiv.org/abs/2505.21318) [find](https://scholar.google.com/scholar?q=Hao+Li%2C+He+Cao%2C+Bin+Feng%2C+Yanjun+Shao%2C+Xiangru+Tang%2C+Zhiyuan+Yan%2C+Li+Yuan%2C+Yonghong+Tian%2C+and+Yu+Li%2E+2025%2E+Beyond+chemical+qa%3A+Evaluating+llm%E2%80%99s+chemical+reasoning+with+modular+chemical+operations%2E+arX)
26. Xuan Liu, Siru Ouyang, Xianrui Zhong, Jiawei Han, and Huimin Zhao. 2025. Fgbench: A dataset and benchmark for molecular property reasoning at functional group-level in large language models. arXiv preprint arXiv:2508.01055. [find](https://scholar.google.com/scholar?q=Xuan+Liu%2C+Siru+Ouyang%2C+Xianrui+Zhong%2C+Jiawei+Han%2C+and+Huimin+Zhao%2E+2025%2E+Fgbench%3A+A+dataset+and+benchmark+for+molecular+property+reasoning+at+functional+group%2Dlevel+in+large+language+models%2E+arXiv+pre)
27. Micha Livne, Zulfat Miftahutdinov, Elena Tutubalina, Maksim Kuznetsov, Daniil Polykovskiy, Annika Brundyn, Aastha Jhunjhunwala, Anthony Costa, Alex Aliper, Alán Aspuru-Guzik, and 1 others. 2024. nach0: multimodal natural and chemical languages foundation model. Chemical Science, 15(22):8380–8389. [find](https://scholar.google.com/scholar?q=Micha+Livne%2C+Zulfat+Miftahutdinov%2C+Elena+Tutubalina%2C+Maksim+Kuznetsov%2C+Daniil+Polykovskiy%2C+Annika+Brundyn%2C+Aastha+Jhunjhunwala%2C+Anthony+Costa%2C+Alex+Aliper%2C+Al%C3%A1n+Aspuru%2DGuzik%2C+and+1+others%2E+2024%2E+nach0)
28. Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, and Yu Li. 2024. Moleculeqa: A dataset to evaluate factual accuracy in molecular comprehension. arXiv preprint arXiv:2403.08192. [find](https://scholar.google.com/scholar?q=Xingyu+Lu%2C+He+Cao%2C+Zijing+Liu%2C+Shengyuan+Bai%2C+Leqing+Chen%2C+Yuan+Yao%2C+Hai%2DTao+Zheng%2C+and+Yu+Li%2E+2024%2E+Moleculeqa%3A+A+dataset+to+evaluate+factual+accuracy+in+molecular+comprehension%2E+arXiv+preprint+arXiv)
29. Naoto Usuyama, Cliff Wong, Sheng Zhang, Tristan Naumann, and Hoifung Poon. 2025. Biomedical natural language processing in the era of large language models. Annual Review of Biomedical Data Science, 8. [find](https://scholar.google.com/scholar?q=Naoto+Usuyama%2C+Cliff+Wong%2C+Sheng+Zhang%2C+Tristan+Naumann%2C+and+Hoifung+Poon%2E+2025%2E+Biomedical+natural+language+processing+in+the+era+of+large+language+models%2E+Annual+Review+of+Biomedical+Data+Science%2C+8)
30. Yuyang Wu, Jinhui Ye, Shuhao Zhang, Lu Dai, Yonatan Bisk, and Olexandr Isayev. 2025. Molerr2fix: Benchmarking llm trustworthiness in chemistry via modular error detection, localization, explanation, and correction. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Proces… [find](https://scholar.google.com/scholar?q=Yuyang+Wu%2C+Jinhui+Ye%2C+Shuhao+Zhang%2C+Lu+Dai%2C+Yonatan+Bisk%2C+and+Olexandr+Isayev%2E+2025%2E+Molerr2fix%3A+Benchmarking+llm+trustworthiness+in+chemistry+via+modular+error+detection%2C+localization%2C+explanation%2C+a)
31. Michihiro Yasunaga, Antoine Bosselut, Hongyu Ren, Xikun Zhang, Christopher D Manning, Percy S Liang, and Jure Leskovec. 2022. Deep bidirectional language-knowledge graph pretraining. Advances in Neural Information Processing Systems, 35:37309–37323. [find](https://scholar.google.com/scholar?q=Michihiro+Yasunaga%2C+Antoine+Bosselut%2C+Hongyu+Ren%2C+Xikun+Zhang%2C+Christopher+D+Manning%2C+Percy+S+Liang%2C+and+Jure+Leskovec%2E+2022%2E+Deep+bidirectional+language%2Dknowledge+graph+pretraining%2E+Advances+in+Neura)
32. Botao Yu, Frazier N Baker, Ziqi Chen, Xia Ning, and Huan Sun. 2024. Llasmol: Advancing large language models for chemistry with a large-scale, comprehensive, high-quality instruction tuning dataset. arXiv preprint arXiv:2402.09391. [find](https://scholar.google.com/scholar?q=Botao+Yu%2C+Frazier+N+Baker%2C+Ziqi+Chen%2C+Xia+Ning%2C+and+Huan+Sun%2E+2024%2E+Llasmol%3A+Advancing+large+language+models+for+chemistry+with+a+large%2Dscale%2C+comprehensive%2C+high%2Dquality+instruction+tuning+dataset%2E+a)
33. Shen Yuan, Shukai Gong, and Hongteng Xu. 2025. Uspto-llm: A large language model-assisted information-enriched chemical reaction dataset. In Companion Proceedings of the ACM on Web Conference 2025, pages 817–820. [find](https://scholar.google.com/scholar?q=Shen+Yuan%2C+Shukai+Gong%2C+and+Hongteng+Xu%2E+2025%2E+Uspto%2Dllm%3A+A+large+language+model%2Dassisted+information%2Denriched+chemical+reaction+dataset%2E+In+Companion+Proceedings+of+the+ACM+on+Web+Conference+2025%2C+pa)
34. Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, and Shirui Pan. 2023. Reasoning on graphs: Faithful and interpretable large language model reasoning. arXiv preprint arXiv:2310.01061. [find](https://scholar.google.com/scholar?q=Linhao+Luo%2C+Yuan%2DFang+Li%2C+Gholamreza+Haffari%2C+and+Shirui+Pan%2E+2023%2E+Reasoning+on+graphs%3A+Faithful+and+interpretable+large+language+model+reasoning%2E+arXiv+preprint+arXiv%3A2310%2E01061%2E)
35. Alan C Marco, Amanda Myers, Stuart JH Graham, Paul D’Agostino, and Kirsten Apple. 2015. The uspto patent assignment dataset: Descriptions and analysis. [find](https://scholar.google.com/scholar?q=Alan+C+Marco%2C+Amanda+Myers%2C+Stuart+JH+Graham%2C+Paul+D%E2%80%99Agostino%2C+and+Kirsten+Apple%2E+2015%2E+The+uspto+patent+assignment+dataset%3A+Descriptions+and+analysis%2E)
36. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2024. [Unifying large language models and knowledge graphs: A roadmap](https://md.research.elamur.ai/free/en/papers/pan-2023-unifying-large-language-models-knowledge/). IEEE Transactions on Knowledge and Data Engineering, 36(7):3580–3599.
37. Di Zhang, Wei Liu, Qian Tan, Jingdan Chen, Hang Yan, Yuliang Yan, Jiatong Li, Weiran Huang, Xiangyu Yue, Wanli Ouyang, and 1 others. 2024. Chemllm: A chemical large language model. arXiv preprint arXiv:2402.06852. [find](https://scholar.google.com/scholar?q=Di+Zhang%2C+Wei+Liu%2C+Qian+Tan%2C+Jingdan+Chen%2C+Hang+Yan%2C+Yuliang+Yan%2C+Jiatong+Li%2C+Weiran+Huang%2C+Xiangyu+Yue%2C+Wanli+Ouyang%2C+and+1+others%2E+2024%2E+Chemllm%3A+A+chemical+large+language+model%2E+arXiv+preprint+arXi)
38. Nicholas T Runcie, Charlotte M Deane, and Fergus Imrie. 2025. Assessing the chemical intelligence of large language models. Journal of Chemical Information and Modeling, 66(1):216–227. [find](https://scholar.google.com/scholar?q=Nicholas+T+Runcie%2C+Charlotte+M+Deane%2C+and+Fergus+Imrie%2E+2025%2E+Assessing+the+chemical+intelligence+of+large+language+models%2E+Journal+of+Chemical+Information+and+Modeling%2C+66%281%29%3A216%E2%80%93227%2E)
39. Qiang Zhang, Keyan Ding, Tianwen Lv, Xinda Wang, Qingyu Yin, Yiwen Zhang, Jing Yu, Yuhao Wang, Xiaotong Li, Zhuoyi Xiang, and 1 others. 2025. Scientific large language models: A survey on biological & chemical domains. ACM Computing Surveys, 57(6):1–38. [find](https://scholar.google.com/scholar?q=Qiang+Zhang%2C+Keyan+Ding%2C+Tianwen+Lv%2C+Xinda+Wang%2C+Qingyu+Yin%2C+Yiwen+Zhang%2C+Jing+Yu%2C+Yuhao+Wang%2C+Xiaotong+Li%2C+Zhuoyi+Xiang%2C+and+1+others%2E+2025%2E+Scientific+large+language+models%3A+A+survey+on+biological+%26)
40. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M Ni, Heung-Yeung Shum, and Jian Guo. 2023. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. arXiv preprint arXiv:2307.07697. [find](https://scholar.google.com/scholar?q=Jiashuo+Sun%2C+Chengjin+Xu%2C+Lumingyuan+Tang%2C+Saizhuo+Wang%2C+Chen+Lin%2C+Yeyun+Gong%2C+Lionel+M+Ni%2C+Heung%2DYeung+Shum%2C+and+Jian+Guo%2E+2023%2E+Think%2Don%2Dgraph%3A+Deep+and+responsible+reasoning+of+large+language+model)
41. Zihan Zhao, Bo Chen, Ziping Wan, Lu Chen, Xuanze Lin, Shiyang Yu, Situo Zhang, Da Ma, Zichen Zhu, Danyang Zhang, and 1 others. 2025. Chemdfm-r: An chemical reasoner llm enhanced with atomized chemical knowledge. arXiv e-prints, pages arXiv– 2507. [find](https://scholar.google.com/scholar?q=Zihan+Zhao%2C+Bo+Chen%2C+Ziping+Wan%2C+Lu+Chen%2C+Xuanze+Lin%2C+Shiyang+Yu%2C+Situo+Zhang%2C+Da+Ma%2C+Zichen+Zhu%2C+Danyang+Zhang%2C+and+1+others%2E+2025%2E+Chemdfm%2Dr%3A+An+chemical+reasoner+llm+enhanced+with+atomized+chemical)

*Updated 1 November 2026*