---
title: "Language agents achieve superhuman synthesis of scientific"
description: "The authors address this with an evaluation framework that compares an AI agent… 85.2% precision. 43 references, cited by 43 papers here."
authors: ["Michael D. Skarlinski; Sam Cox; Jon M. Laurent; James D. Braza; Michaela Hinks; Michael J. Hammerling; Manvitha Ponnapati; Samuel G. Rodriques;", "Andrew D. White"]
year: 2024
venue: "arXiv:2409.13740"
source: "https://arxiv.org/abs/2409.13740"
doi: "10.48550/arxiv.2409.13740"
arxiv: "2409.13740"
licence: "CC BY-SA 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by-sa/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/skarlinski-2024-language-agents-achieve-superhuman/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/skarlinski-2024-language-agents-achieve-superhuman/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/5/) / Language agents achieve superhuman synthesis of scientific knowledge

# Language agents achieve superhuman synthesis of scientific knowledge

**Authors:** Michael D. Skarlinski; Sam Cox; Jon M. Laurent; James D. Braza; Michaela Hinks; Michael J. Hammerling; Manvitha Ponnapati; Samuel G. Rodriques; and [Andrew D. White](https://md.research.elamur.ai/free/en/authors/andrew-d-white/) · **Year:** 2024 · **Venue:** arXiv:2409.13740 · **Licence:** [CC BY-SA 4.0 (arXiv)](http://creativecommons.org/licenses/by-sa/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2409.13740) · [PDF](https://arxiv.org/pdf/2409.13740) · [DOI 10.48550/arxiv.2409.13740](https://doi.org/10.48550/arxiv.2409.13740) · [arXiv 2409.13740](https://arxiv.org/abs/2409.13740) · [OpenAlex](https://openalex.org/W4403795293)

**Citations:** 46 citations (OpenAlex, 2026-10-14) · [43](https://md.research.elamur.ai/free/en/papers/skarlinski-2024-language-agents-achieve-superhuman/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Can LLM-based systems be trusted to search, summarize, and critically examine scientific literature? The authors address this with an evaluation framework that compares an AI agent directly against PhD-level experts on three realistic tasks: answering questions that require retrieval from full-text papers, writing cited Wikipedia-style topic articles, and detecting contradictions between published claims. To support this, they built LitQA2, a difficult multiple-choice benchmark whose answers sit in paper bodies rather than abstracts. They also developed PaperQA2, an agentic retrieval-augmented system. It splits retrieval into separate tools: paper search, evidence gathering with LLM reranking and contextual summarization (RCS), citation-graph traversal, and answer generation. This lets the agent iterate on its searches before it commits to an answer. PaperQA2 beat human experts in precision on LitQA2 and was comparable to them in accuracy. Its generated articles (WikiCrow) were judged more factual than human-written Wikipedia pages. A derived system, ContraCrow, found contradictions across biology papers at scale. The work suggests language agents can now match or outperform domain experts on substantive literature-research tasks, at a modest cost per query.

## Key points
- **LitQA2 benchmark:** 248 expert-written questions with a built-in "insufficient information" option. The questions were filtered so that no alternative source could answer them. A held-out batch of 101 questions, written after most engineering was done, showed no sign of overfitting.
- **PaperQA2 vs. experts:** PaperQA2 reached 85.2% precision and 66.0% accuracy, reading about 14.5 papers per question. Human experts scored 73.8% precision and 67.7% accuracy. The precision gap is statistically significant; the accuracy difference is not.
- **System design:** PaperQA2 uses Grobid for document parsing, dense top-k retrieval followed by RCS, and a Citation Traversal tool. Removing agentic control or citation traversal reduced performance. PaperQA2 outperformed Perplexity, Elicit, the original PaperQA, and non-RAG frontier models.
- **ContraCrow contradiction detection:** Across 93 biology papers, it found about 35 claims and 2.34 contradictions per paper. Experts confirmed roughly 70% of these, which implies a lower bound of 1.64 validated contradictions per paper. ContraCrow agreed with humans less often than humans agreed with each other, mainly because of overconfidence.
- **Cost and availability:** Each query costs about $1–3. The code is released as `paperqa` on GitHub, and the WikiCrow articles and evaluation data are publicly available.

*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

- [University of Rochester](https://md.research.elamur.ai/free/en/universities/university-of-rochester/) — University, Rochester, United States · 43 works · 7,874 citations
- [Future House, Inc.](https://md.research.elamur.ai/free/en/ngos/future-house-inc/) — Nonprofit, San Francisco, United States · 4 works · 548 citations
- [The Francis Crick Institute](https://md.research.elamur.ai/free/en/labs/the-francis-crick-institute/) — Research institute, London, United Kingdom · 2 works · 198 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

## Cite

Cite as: Michael D. Skarlinski; Sam Cox; Jon M. Laurent; James D. Braza; Michaela Hinks; Michael J. Hammerling; Manvitha Ponnapati; Samuel G. Rodriques; and Andrew D. White. 2024. Language agents achieve superhuman synthesis of scientific knowledge. arXiv:2409.13740.

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

```bibtex
@misc{rodriques2024language,
  title = {{Language agents achieve superhuman synthesis of scientific knowledge}},
  author = {Michael D. Skarlinski; Sam Cox; Jon M. Laurent; James D. Braza; Michaela Hinks; Michael J. Hammerling; Manvitha Ponnapati; Samuel G. Rodriques; and Andrew D. White},
  year = {2024},
  doi = {10.48550/arxiv.2409.13740},
  eprint = {2409.13740},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2409.13740}
}
```

- [← previous Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs](https://md.research.elamur.ai/free/en/papers/jin-2024-graph-chain-thought-augmenting-large/)
- [next → LVBench: An Extreme Long Video Understanding Benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-lvbench-extreme-long-video-understanding/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/5/)

## References

43 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. [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, 2023.
2. Yijia Shao, Yucheng Jiang, Theodore A Kanell, Peter Xu, Omar Khattab, and Monica S Lam. [Assisting in writing wikipedia-like articles from scratch with large language models](https://md.research.elamur.ai/free/en/papers/shao-2024-assisting-writing-wikipedia-like-articles/). arXiv preprint arXiv:2402.14207, 2024.
3. Kyle Lo, Joseph Chee Chang, Andrew Head, Jonathan Bragg, Amy X. Zhang, Cassidy Trier, Chloe Anastasiades, Tal August, Russell Authur, Danielle Bragg, Erin Bransom, Isabel Cachola, Stefan Candra, Yoganand Chandrasekhar, Yen-Sung Chen, Evie (Yu-Yen) Cheng, Yvonne Chou, Doug Downey, Rob Evans, Raymond… — [arXiv:2303.14334](https://arxiv.org/abs/2303.14334) [find](https://scholar.google.com/scholar?q=Kyle+Lo%2C+Joseph+Chee+Chang%2C+Andrew+Head%2C+Jonathan+Bragg%2C+Amy+X%2E+Zhang%2C+Cassidy+Trier%2C+Chloe+Anastasiades%2C+Tal+August%2C+Russell+Authur%2C+Danielle+Bragg%2C+Erin+Bransom%2C+Isabel+Cachola%2C+Stefan+Candra%2C+Yogan)
4. SM Tonmoy, SM Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, and Amitava Das. [A comprehensive survey of hallucination mitigation techniques in large language models](https://md.research.elamur.ai/free/en/papers/tonmoy-2024-comprehensive-survey-hallucination-mitigation-techniques/). arXiv preprint arXiv:2401.01313, 2024.
5. Matthew Dahl, Varun Magesh, Mirac Suzgun, and Daniel E Ho. [Large legal fictions: Profiling legal hallucinations in large language models](https://md.research.elamur.ai/free/en/papers/dahl-2024-large-legal-fictions-profiling-legal/). Journal of Legal Analysis, 16(1):64–93, 2024.
6. Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William Cohen, and Xinghua Lu. [PubMedQA: A dataset for biomedical research question answering](https://md.research.elamur.ai/free/en/papers/jin-2019-pubmedqa-dataset-biomedical-research-question/). In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan, editors, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9t…
7. Anastasia Krithara, Anastasios Nentidis, Konstantinos Bougiatiotis, and Georgios Paliouras. [Bioasq-qa: A manually curated corpus for biomedical question answering](https://md.research.elamur.ai/free/en/papers/krithara-2023-bioasq-qa-manually-curated-corpus/). Scientific Data, 10(1):170, 2023.
8. Qiao Jin, Bhuwan Dhingra, Zhengping Liu, William W Cohen, and Xinghua Lu. [Pubmedqa: A dataset for biomedical research question answering](https://md.research.elamur.ai/free/en/papers/jin-2019-pubmedqa-dataset-biomedical-research-question/). arXiv preprint arXiv:1909.06146, 2019.
9. Shuai Wang, Yi He, Zi Chen, Yanzhang Li, Jingping Zhao, and Luxian Lyu. Pleiotropic action of genetic variation in znf804a on brain structure: a meta-analysis of magnetic resonance imaging studies. Neuropsychiatric Disease and Treatment, pages 721–729, 2019. [find](https://scholar.google.com/scholar?q=Shuai+Wang%2C+Yi+He%2C+Zi+Chen%2C+Yanzhang+Li%2C+Jingping+Zhao%2C+and+Luxian+Lyu%2E+Pleiotropic+action+of+genetic+variation+in+znf804a+on+brain+structure%3A+a+meta%2Danalysis+of+magnetic+resonance+imaging+studies%2E+Ne)
10. Qinling Wei, Meng Li, Zhuang Kang, Leijun Li, Feici Diao, Ruibin Zhang, Junjing Wang, Liangrong Zheng, Xue Wen, Jinbei Zhang, et al. Znf804a rs1344706 is associated with cortical thickness, surface area, and cortical volume of the unmedicated first episode schizophrenia and healthy controls. America… [find](https://scholar.google.com/scholar?q=Qinling+Wei%2C+Meng+Li%2C+Zhuang+Kang%2C+Leijun+Li%2C+Feici+Diao%2C+Ruibin+Zhang%2C+Junjing+Wang%2C+Liangrong+Zheng%2C+Xue+Wen%2C+Jinbei+Zhang%2C+et+al%2E+Znf804a+rs1344706+is+associated+with+cortical+thickness%2C+surface+ar)
11. Jon M. Laurent, Joseph D. Janizek, Michael Ruzo, Michaela M. Hinks, Michael J. Hammerling, Siddharth Narayanan, Manvitha Ponnapati, Andrew D. White, and Samuel G. Rodriques. [Lab-bench: Measuring capabilities of language models for biology research](https://md.research.elamur.ai/free/en/papers/laurent-2024-lab-bench-measuring-capabilities/). arXiv preprint arXiv:2407.10362, 2024.
12. Yuwei Wan, Aswathy Ajith, Yixuan Liu, Ke Lu, Clara Grazian, Bram Hoex, Wenjie Zhang, Chunyu Kit, Tong Xie, and Ian Foster. Sciqag: A framework for auto-generated scientific question answering dataset with fine-grained evaluation. arXiv preprint arXiv:2405.09939, 2024. — [arXiv:2405.09939](https://arxiv.org/abs/2405.09939) [find](https://scholar.google.com/scholar?q=Yuwei+Wan%2C+Aswathy+Ajith%2C+Yixuan+Liu%2C+Ke+Lu%2C+Clara+Grazian%2C+Bram+Hoex%2C+Wenjie+Zhang%2C+Chunyu+Kit%2C+Tong+Xie%2C+and+Ian+Foster%2E+Sciqag%3A+A+framework+for+auto%2Dgenerated+scientific+question+answering+dataset+)
13. Pranav Rajpurkar, Robin Jia, and Percy Liang. Know what you don’t know: Unanswerable questions for squad. arXiv preprint arXiv:1806.[03822, 2018](https://md.research.elamur.ai/free/en/papers/rajpurkar-2018-know-what-you-don-t/).
14. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. [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, 33:9459–9474, 2020.
15. Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. [Retrieval augmentation reduces hallucination in conversation](https://md.research.elamur.ai/free/en/papers/shuster-2021-retrieval-augmentation-reduces-hallucination-conversation/). arXiv preprint arXiv:2104.07567, 2021.
16. Yunfan Gao, Tao Sheng, Youlin Xiang, Yun Xiong, Haofen Wang, and Jiawei Zhang. Chat-rec: Towards interactive and explainable llms-augmented recommender system. arXiv preprint arXiv:2303.14524, 2023. — [arXiv:2303.14524](https://arxiv.org/abs/2303.14524) [find](https://scholar.google.com/scholar?q=Yunfan+Gao%2C+Tao+Sheng%2C+Youlin+Xiang%2C+Yun+Xiong%2C+Haofen+Wang%2C+and+Jiawei+Zhang%2E+Chat%2Drec%3A+Towards+interactive+and+explainable+llms%2Daugmented+recommender+system%2E+arXiv+preprint+arXiv%3A2303%2E14524%2C+2023%2E+%E2%80%94)
17. Jakub Lála, Odhran O’Donoghue, Aleksandar Shtedritski, Sam Cox, Samuel G Rodriques, and Andrew D White. [Paperqa: Retrieval-augmented generative agent for scientific research](https://md.research.elamur.ai/free/en/papers/lala-2023-paperqa-retrieval-augmented-generative/). arXiv preprint arXiv:2312.07559, 2023.
18. Ehud Karpas, Omri Abend, Yonatan Belinkov, Barak Lenz, Opher Lieber, Nir Ratner, Yoav Shoham, Hofit Bata, Yoav Levine, Kevin Leyton-Brown, et al. Mrkl systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning. arXiv preprin… — [arXiv:2205.00445](https://arxiv.org/abs/2205.00445) [find](https://scholar.google.com/scholar?q=Ehud+Karpas%2C+Omri+Abend%2C+Yonatan+Belinkov%2C+Barak+Lenz%2C+Opher+Lieber%2C+Nir+Ratner%2C+Yoav+Shoham%2C+Hofit+Bata%2C+Yoav+Levine%2C+Kevin+Leyton%2DBrown%2C+et+al%2E+Mrkl+systems%3A+A+modular%2C+neuro%2Dsymbolic+architecture+t)
19. Grobid. [https://github.com/kermitt2/grobid](https://github.com/kermitt2/grobid), 2008–2023. [↗](https://github.com/kermitt2/grobid)
20. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H Chi, Nathanael Schärli, and Denny Zhou. [Large language models can be easily distracted by irrelevant context](https://md.research.elamur.ai/free/en/papers/shi-2023-large-language-models-easily-distracted/). In International Conference on Machine Learning, pages 31210–31227. PMLR, 2023.
21. Perplexity. [https://www.perplexity.ai/](https://www.perplexity.ai/). Accessed: 2024-07-10. [↗](https://www.perplexity.ai/)
22. Elicit. [https://www.elicit.com/](https://www.elicit.com/). Accessed: 2024-07-10. [↗](https://www.elicit.com/)
23. Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, and Weizhu Chen. [Generation-augmented retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/mao-2020-generation-augmented-retrieval-open-domain/). arXiv preprint arXiv:2009.08553, 2020.
24. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12:157–173, 2024.
25. Introducing the next generation of Claude — anthropic.com. claude-3-family. [Accessed 13-07-2024]. [https://www.anthropic.com/news/](https://www.anthropic.com/news/) [↗](https://www.anthropic.com/news/)
26. John Giorgi, Luca Soldaini, Bo Wang, Gary D Bader, Kyle Lo, Lucy Lu Wang, and Arman Cohan. Exploring the challenges of open domain multi-document summarization. ArXiv, abs/2212.10526, 2022. — [arXiv:2212.10526](https://arxiv.org/abs/2212.10526) [find](https://scholar.google.com/scholar?q=John+Giorgi%2C+Luca+Soldaini%2C+Bo+Wang%2C+Gary+D+Bader%2C+Kyle+Lo%2C+Lucy+Lu+Wang%2C+and+Arman+Cohan%2E+Exploring+the+challenges+of+open+domain+multi%2Ddocument+summarization%2E+ArXiv%2C+abs%2F2212%2E10526%2C+2022%2E+%E2%80%94+%5BarXiv%3A2)
27. Andreas Vlachos and Sebastian Riedel. [Fact checking: Task definition and dataset construction](https://md.research.elamur.ai/free/en/papers/vlachos-2014-fact-checking-task-definition-dataset/). In Proceedings of the ACL 2014 workshop on language technologies and computational social science, pages 18–22, 2014.
28. William Ferreira and Andreas Vlachos. [Emergent: a novel data-set for stance classification](https://md.research.elamur.ai/free/en/papers/ferreira-2016-emergent-novel-data-set-stance/). In Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: Human language technologies. ACL, 2016.
29. Kashyap Popat, Subhabrata Mukherjee, Jannik Strötgen, and Gerhard Weikum. Where the truth lies: Explaining the credibility of emerging claims on the web and social media. In Proceedings of the 26th international conference on world wide web companion, pages 1003–1012, 2017. [find](https://scholar.google.com/scholar?q=Kashyap+Popat%2C+Subhabrata+Mukherjee%2C+Jannik+Str%C3%B6tgen%2C+and+Gerhard+Weikum%2E+Where+the+truth+lies%3A+Explaining+the+credibility+of+emerging+claims+on+the+web+and+social+media%2E+In+Proceedings+of+the+26th+in)
30. Michael Schlichtkrull, Zhijiang Guo, and Andreas Vlachos. [Averitec: A dataset for real-world claim verification with evidence from the web](https://md.research.elamur.ai/free/en/papers/schlichtkrull-2023-averitec-dataset-real-world-claim/). Advances in Neural Information Processing Systems, 36, 2024.
31. David Wadden, Shanchuan Lin, Kyle Lo, Lucy Lu Wang, Madeleine van Zuylen, Arman Cohan, and Hannaneh Hajishirzi. [Fact or fiction: Verifying scientific claims](https://md.research.elamur.ai/free/en/papers/wadden-2020-fact-or-fiction-verifying-scientific/). arXiv preprint arXiv:2004.14974, 2020.
32. David Wadden, Kyle Lo, Lucy Lu Wang, Arman Cohan, Iz Beltagy, and Hannaneh Hajishirzi. Multivers: Improving scientific claim verification with weak supervision and full-document context. arXiv preprint arXiv:2112.01640, 2021. [find](https://scholar.google.com/scholar?q=David+Wadden%2C+Kyle+Lo%2C+Lucy+Lu+Wang%2C+Arman+Cohan%2C+Iz+Beltagy%2C+and+Hannaneh+Hajishirzi%2E+Multivers%3A+Improving+scientific+claim+verification+with+weak+supervision+and+full%2Ddocument+context%2E+arXiv+preprin)
33. Bhashithe Abeysinghe and Ruhan Circi. The challenges of evaluating llm applications: An analysis of automated, human, and llm-based approaches. arXiv preprint arXiv:2406.03339, 2024. — [arXiv:2406.03339](https://arxiv.org/abs/2406.03339) [find](https://scholar.google.com/scholar?q=Bhashithe+Abeysinghe+and+Ruhan+Circi%2E+The+challenges+of+evaluating+llm+applications%3A+An+analysis+of+automated%2C+human%2C+and+llm%2Dbased+approaches%2E+arXiv+preprint+arXiv%3A2406%2E03339%2C+2024%2E+%E2%80%94+%5BarXiv%3A2406%2E033)
34. Lydia Kriegl, David Horst, Jana A Reiche, Jutta Engel, Thomas Kirchner, and Andreas Jung. Lef-1 and tcf4 expression correlate inversely with survival in colorectal cancer. Journal of translational medicine, 8:1–8, 2010. [find](https://scholar.google.com/scholar?q=Lydia+Kriegl%2C+David+Horst%2C+Jana+A+Reiche%2C+Jutta+Engel%2C+Thomas+Kirchner%2C+and+Andreas+Jung%2E+Lef%2D1+and+tcf4+expression+correlate+inversely+with+survival+in+colorectal+cancer%2E+Journal+of+translational+med)
35. Albert Y Lin, Mei-Sze Chua, Yoon-La Choi, William Yeh, Young H Kim, Raymond Azzi, Gregg A Adams, Kristin Sainani, Matt van de Rijn, Samuel K So, et al. Comparative profiling of primary colorectal carcinomas and liver metastases identifies lef1 as a prognostic biomarker. PloS one, 6(2):e16636, 2011. [find](https://scholar.google.com/scholar?q=Albert+Y+Lin%2C+Mei%2DSze+Chua%2C+Yoon%2DLa+Choi%2C+William+Yeh%2C+Young+H+Kim%2C+Raymond+Azzi%2C+Gregg+A+Adams%2C+Kristin+Sainani%2C+Matt+van+de+Rijn%2C+Samuel+K+So%2C+et+al%2E+Comparative+profiling+of+primary+colorectal+carc)
36. Wen-Juan Wang, Yu Yao, Li-Li Jiang, Ting-Hua Hu, Jie-Qun Ma, Zhi-Ping Ruan, Tao Tian, Hui Guo, Shu-Hong Wang, and Ke-Jun Nan. Increased lef1 expression and decreased notch2 expression are strong predictors of poor outcomes in colorectal cancer patients. Disease markers, 35(5):395–405, 2013. [find](https://scholar.google.com/scholar?q=Wen%2DJuan+Wang%2C+Yu+Yao%2C+Li%2DLi+Jiang%2C+Ting%2DHua+Hu%2C+Jie%2DQun+Ma%2C+Zhi%2DPing+Ruan%2C+Tao+Tian%2C+Hui+Guo%2C+Shu%2DHong+Wang%2C+and+Ke%2DJun+Nan%2E+Increased+lef1+expression+and+decreased+notch2+expression+are+strong+predi)
37. Wen-Juan Wang, Yu Yao, Li-Li Jiang, Ting-Hua Hu, Jie-Qun Ma, Zi-Jun Liao, Jun-Tao Yao, Dong-Fan Li, Shu-Hong Wang, and Ke-Jun Nan. Knockdown of lymphoid enhancer factor 1 inhibits colon cancer progression in vitro and in vivo. PLoS One, 8(10):e76596, 2013. [find](https://scholar.google.com/scholar?q=Wen%2DJuan+Wang%2C+Yu+Yao%2C+Li%2DLi+Jiang%2C+Ting%2DHua+Hu%2C+Jie%2DQun+Ma%2C+Zi%2DJun+Liao%2C+Jun%2DTao+Yao%2C+Dong%2DFan+Li%2C+Shu%2DHong+Wang%2C+and+Ke%2DJun+Nan%2E+Knockdown+of+lymphoid+enhancer+factor+1+inhibits+colon+cancer+progres)
38. Taher R Kermanshahi, Priya Jayachandran, Daniel T Chang, and Reet Pai. Lef-1 is frequently expressed in colorectal carcinoma and not in other gastrointestinal tract adenocarcinomas: an immunohistochemical survey of 602 gastrointestinal tract neoplasms. Applied Immunohistochemistry & Molecular Morpho… [find](https://scholar.google.com/scholar?q=Taher+R+Kermanshahi%2C+Priya+Jayachandran%2C+Daniel+T+Chang%2C+and+Reet+Pai%2E+Lef%2D1+is+frequently+expressed+in+colorectal+carcinoma+and+not+in+other+gastrointestinal+tract+adenocarcinomas%3A+an+immunohistochem)
39. YS Cheng, Mary F Becker-Manley, Theresa P Chow, and Deborah C Horan. Affinity purification of an interferon-induced human guanylate-binding protein and its characterization. Journal of Biological Chemistry, 260(29):15834– 15839, 1985. [find](https://scholar.google.com/scholar?q=YS+Cheng%2C+Mary+F+Becker%2DManley%2C+Theresa+P+Chow%2C+and+Deborah+C+Horan%2E+Affinity+purification+of+an+interferon%2Dinduced+human+guanylate%2Dbinding+protein+and+its+characterization%2E+Journal+of+Biological+Chem)
40. Nathalie Britzen-Laurent, Michael Bauer, Valeria Berton, Nicole Fischer, Adrian Syguda, Simone Reipschläger, Elisabeth Naschberger, Christian Herrmann, and Michael Stürzl. Intracellular trafficking of guanylate-binding proteins is regulated by heterodimerization in a hierarchical manner. PloS one, 5… [find](https://scholar.google.com/scholar?q=Nathalie+Britzen%2DLaurent%2C+Michael+Bauer%2C+Valeria+Berton%2C+Nicole+Fischer%2C+Adrian+Syguda%2C+Simone+Reipschl%C3%A4ger%2C+Elisabeth+Naschberger%2C+Christian+Herrmann%2C+and+Michael+St%C3%BCrzl%2E+Intracellular+trafficking+of)
41. Nir Modiano, Yanping E Lu, and Peter Cresswell. Golgi targeting of human guanylate-binding protein-1 requires nucleotide binding, isoprenylation, and an ifn-γ-inducible cofactor. Proceedings of the National Academy of Sciences, 102(24):8680–8685, 2005. [find](https://scholar.google.com/scholar?q=Nir+Modiano%2C+Yanping+E+Lu%2C+and+Peter+Cresswell%2E+Golgi+targeting+of+human+guanylate%2Dbinding+protein%2D1+requires+nucleotide+binding%2C+isoprenylation%2C+and+an+ifn%2D%CE%B3%2Dinducible+cofactor%2E+Proceedings+of+the+Na)
42. Elisabeth Naschberger, Clara Lubeseder-Martellato, Nadine Meyer, Ruth Gessner, Elisabeth Kremmer, Andrè Gessner, and Michael Stürzl. Human guanylate binding protein-1 is a secreted gtpase present in increased concentrations in the cerebrospinal fluid of patients with bacterial meningitis. The Americ… [find](https://scholar.google.com/scholar?q=Elisabeth+Naschberger%2C+Clara+Lubeseder%2DMartellato%2C+Nadine+Meyer%2C+Ruth+Gessner%2C+Elisabeth+Kremmer%2C+Andr%C3%A8+Gessner%2C+and+Michael+St%C3%BCrzl%2E+Human+guanylate+binding+protein%2D1+is+a+secreted+gtpase+present+in+i)
43. Luca Schelle, João Vasco Côrte-Real, Pedro José Esteves, Joana Abrantes, and Hanna-Mari Baldauf. Functional cross-species conservation of guanylate-binding proteins in innate immunity. Medical Microbiology and Immunology, 212(2):141–152, 2023. Methods 8.1 PaperQA Implementation and Parameters [find](https://scholar.google.com/scholar?q=Luca+Schelle%2C+Jo%C3%A3o+Vasco+C%C3%B4rte%2DReal%2C+Pedro+Jos%C3%A9+Esteves%2C+Joana+Abrantes%2C+and+Hanna%2DMari+Baldauf%2E+Functional+cross%2Dspecies+conservation+of+guanylate%2Dbinding+proteins+in+innate+immunity%2E+Medical+Microbi)

*Updated 2 November 2026*