---
title: "HypER — paper by Vasu et al. (2025) — summary and ideas"
description: "LLM-based hypothesis generators usually condition on retrieved papers. 38 references, cited by 5 papers here."
authors: ["Rosni Vasu", "Chandrayee Basu", "Bhavana Dalvi Mishra", "Cristina Sarasua", "Peter Clark", "Abraham Bernstein"]
year: 2025
venue: "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/2025.emnlp-main.1292/"
doi: "10.18653/v1/2025.emnlp-main.1292"
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/vasu-2025-hyper-literature-grounded-hypothesis-generation/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/vasu-2025-hyper-literature-grounded-hypothesis-generation/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/11/) / HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance

# HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance

**Authors:** Rosni Vasu, Chandrayee Basu, [Bhavana Dalvi Mishra](https://md.research.elamur.ai/free/en/authors/bhavana-dalvi-mishra/), Cristina Sarasua, [Peter Clark](https://md.research.elamur.ai/free/en/authors/peter-clark/) and Abraham Bernstein · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/)) · **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/2025.emnlp-main.1292/) · [PDF](https://aclanthology.org/2025.emnlp-main.1292.pdf) · [DOI 10.18653/v1/2025.emnlp-main.1292](https://doi.org/10.18653/v1/2025.emnlp-main.1292) · [OpenAlex](https://openalex.org/W4416035661)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 5 in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLM-based hypothesis generators usually condition on retrieved papers. They rarely check whether the cited works actually build on one another, which leaves their ideas weakly grounded and hard to trace. This is a serious gap in medicine, where researchers expect clear evidence trails. HypER addresses it with a small language model that learns to reason over chronological chains of paper abstracts before proposing a hypothesis.

The authors started from expert-curated systematic reviews of randomized controlled trials (Wallace et al., 2021). They followed citation links and used an expert-validated teacher LLM to score whether each citing paper is inspired by or depends on its predecessor. Distractor papers that share terminology but not reasoning were added to create invalid chains. The resulting pipeline was then distilled into Phi-3-mini through multitask fine-tuning.

HypER beats its base model at telling valid chains from invalid ones and produces better-grounded hypotheses, which experts rated as feasible and impactful. The work shows that explicit validation of reasoning chains, not semantic similarity alone, can make AI-assisted literature-based discovery more trustworthy.

## Key points
- **Dataset:** 3,523 reasoning chains, expanded from a base set of 359 valid chains, with fine-grained relevance labels (0 irrelevant, 1 inspired, 2 dependent) and curated invalid chains containing controlled distractors.
- **Training tasks:** three jointly trained objectives:
  - one-hop paper-to-paper relevance scoring;
  - chain validation without the target hypothesis (multi-hop-A);
  - chain validation given the target hypothesis (multi-hop-C).
  
  Both validation tasks also locate the papers where the chain breaks.
- **Base model:** HypER_Phi-3-3.8B, built on Phi-3-mini-128k-instruct.
- **Results:**
  - about +22% average absolute F1 over the base model on chain validity;
  - groundedness of 0.327 vs. 0.305 for the base model;
  - expert scores above 3.5 on a 5-point scale, including feasibility 4.22, impact 3.69 and originality 3.21.
- **Similarity is not enough:** invalid chains are roughly 0.98 semantically similar to valid ones.
- **LLM-judge reliability:** agreement between LLM judges and experts was moderate for clarity and impact but weak for originality and feasibility.
- **Comparison with GPT-4o:** an automated comparison put HypER on par for originality (3.01 vs. 3.00) but behind on significance (3.37 vs. 3.84).

*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

- [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) — Research institute, Seattle, United States · 304 works · 106,137 citations
- [Cornell University](https://md.research.elamur.ai/free/en/universities/cornell-university/) — University, Ithaca, United States · 134 works · 65,159 citations
- [University of Zurich](https://md.research.elamur.ai/free/en/universities/university-of-zurich/) — University, Zurich, Switzerland · 80 works · 12,260 citations

📚 Shelves (7): [🖥️ 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 · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 263 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 260 works

🧭 Topics (1): [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 297 works

## Cite

Cite as: Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra, Cristina Sarasua, Peter Clark and Abraham Bernstein. 2025. HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{vasu2025hyper,
  title = {{HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance}},
  author = {Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra, Cristina Sarasua, Peter Clark and Abraham Bernstein},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.1292},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.1292}
}
```

- [← previous Growing Through Experience: Scaling Episodic Grounding in Language Models](https://md.research.elamur.ai/free/en/papers/zhang-2025-growing-through-experience-scaling-episodic/)
- [next → InductionBench: LLMs Fail in the Simplest Complexity Class](https://md.research.elamur.ai/free/en/papers/hua-2025-inductionbench-llms-fail-simplest-complexity/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/11/)

## References

38 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abbi Abdel-Rehim, Hector Zenil, Oghenejokpeme Orhobor, Marie Fisher, Ross J Collins, Elizabeth Bourne, Gareth W Fearnley, Emma Tate, Holly X Smith, Larisa N Soldatova, et al. 2024. Scientific hypothesis generation by a large language model: Laboratory validation in breast cancer treatment. arXiv e-p… [find](https://scholar.google.com/scholar?q=Abbi+Abdel%2DRehim%2C+Hector+Zenil%2C+Oghenejokpeme+Orhobor%2C+Marie+Fisher%2C+Ross+J+Collins%2C+Elizabeth+Bourne%2C+Gareth+W+Fearnley%2C+Emma+Tate%2C+Holly+X+Smith%2C+Larisa+N+Soldatova%2C+et+al%2E+2024%2E+Scientific+hypothes)
2. Marah Abdin, Jyoti Aneja, Hany Awadalla, Ahmed Awadallah, Ammar Ahmad Awan, Nguyen Bach, Amit Bahree, Arash Bakhtiari, Jianmin Bao, Harkirat Behl, et al. 2024. [Phi-3 technical report: A highly capable language model locally on your phone](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-3-technical-report-highly/). arXiv preprint arXiv:2404.14219.
3. Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, and Sung Ju Hwang. 2024a. [Researchagent: Iterative research idea generation over scientific literature with large language models](https://md.research.elamur.ai/free/en/papers/baek-2024-researchagent-iterative-research-idea/). arXiv preprint arXiv:2404.07738.
4. Jinheon Baek, Sujay Kumar Jauhar, Silviu Cucerzan, and Sung Ju Hwang. 2024b. [Researchagent: Iterative research idea generation over scientific literature with large language models](https://md.research.elamur.ai/free/en/papers/baek-2024-researchagent-iterative-research-idea/). ArXiv, abs/2404.07738.
5. Isabelle Bichindaritz, Emin Kansu, and Keith M Sullivan. 1998. Case-based reasoning in care-partner: Gathering evidence for evidence-based medical practice. In European workshop on advances in case-based reasoning, pages 334–345. Springer. [find](https://scholar.google.com/scholar?q=Isabelle+Bichindaritz%2C+Emin+Kansu%2C+and+Keith+M+Sullivan%2E+1998%2E+Case%2Dbased+reasoning+in+care%2Dpartner%3A+Gathering+evidence+for+evidence%2Dbased+medical+practice%2E+In+European+workshop+on+advances+in+case%2Dba)
6. Daniil A Boiko, Robert MacKnight, Ben Kline, and Gabe Gomes. 2023. [Autonomous chemical research with large language models](https://md.research.elamur.ai/free/en/papers/boiko-2023-autonomous-chemical-research-large-language/). Nature, 624(7992):570– 578.
7. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
8. Alireza Ghafarollahi and Markus J Buehler. 2024. Sciagents: Automating scientific discovery through bioinspired multi-agent intelligent graph reasoning. Advanced Materials, page 2413523. [find](https://scholar.google.com/scholar?q=Alireza+Ghafarollahi+and+Markus+J+Buehler%2E+2024%2E+Sciagents%3A+Automating+scientific+discovery+through+bioinspired+multi%2Dagent+intelligent+graph+reasoning%2E+Advanced+Materials%2C+page+2413523%2E)
9. Xuemei Gu and Mario Krenn. 2024. Generation and human-expert evaluation of interesting research ideas using knowledge graphs and large language models. arXiv preprint arXiv:2405.17044. — [arXiv:2405.17044](https://arxiv.org/abs/2405.17044) [find](https://scholar.google.com/scholar?q=Xuemei+Gu+and+Mario+Krenn%2E+2024%2E+Generation+and+human%2Dexpert+evaluation+of+interesting+research+ideas+using+knowledge+graphs+and+large+language+models%2E+arXiv+preprint+arXiv%3A2405%2E17044%2E+%E2%80%94+%5BarXiv%3A2405%2E1)
10. Yu Gu, Robert Tinn, Hao Cheng, Michael Lucas, Naoto Usuyama, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, and Hoifung Poon. 2021. [Domain-specific language model pretraining for biomedical natural language processing](https://md.research.elamur.ai/free/en/papers/gu-2020-domain-specific-language-model-pretraining/). ACM Transactions on Computing for Healthcare (HEALTH), 3(1):1–23.
11. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). arXiv preprint arXiv:2106.09685.
12. Xia Jing, James J Cimino, Vimla L Patel, Yuchun Zhou, Jay H Shubrook, Chang Liu, and Sonsoles De Lacalle. 2024. Data-driven hypothesis generation in clinical research: What we learned from a human subject study? Medical Research Archives, 12(2). [find](https://scholar.google.com/scholar?q=Xia+Jing%2C+James+J+Cimino%2C+Vimla+L+Patel%2C+Yuchun+Zhou%2C+Jay+H+Shubrook%2C+Chang+Liu%2C+and+Sonsoles+De+Lacalle%2E+2024%2E+Data%2Ddriven+hypothesis+generation+in+clinical+research%3A+What+we+learned+from+a+human+sub)
13. Indunil Karunarathna, P Gunasena, T Hapuarachchi, and S Gunathilake. 2024. The evolution of hypotheses in scientific literature: A review of impact and reach. [find](https://scholar.google.com/scholar?q=Indunil+Karunarathna%2C+P+Gunasena%2C+T+Hapuarachchi%2C+and+S+Gunathilake%2E+2024%2E+The+evolution+of+hypotheses+in+scientific+literature%3A+A+review+of+impact+and+reach%2E)
14. Ross D. King, Jem Rowland, Stephen G. Oliver, Michael Young, Wayne Aubrey, Emma Byrne, Maria Liakata, Magdalena Markham, Pinar Pir, Larisa N. Soldatova, Andrew Sparkes, Kenneth E. Whelan, and Amanda Clare. 2009. The automation of science. Science, 324(5923):85–89. [find](https://scholar.google.com/scholar?q=Ross+D%2E+King%2C+Jem+Rowland%2C+Stephen+G%2E+Oliver%2C+Michael+Young%2C+Wayne+Aubrey%2C+Emma+Byrne%2C+Maria+Liakata%2C+Magdalena+Markham%2C+Pinar+Pir%2C+Larisa+N%2E+Soldatova%2C+Andrew+Sparkes%2C+Kenneth+E%2E+Whelan%2C+and+Amanda+C)
15. Sandeep Kumar, Tirthankar Ghosal, Vinayak Goyal, and Asif Ekbal. 2024. [Can large language models unlock novel scientific research ideas?](https://md.research.elamur.ai/free/en/papers/kumar-2025-can-large-language-models-unlock/) arXiv preprint arXiv:2409.06185.
16. Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, et al. 2024. Chain of ideas: Revolutionizing research via novel idea development with llm agents. arXiv preprint arXiv:2410.13185. [find](https://scholar.google.com/scholar?q=Long+Li%2C+Weiwen+Xu%2C+Jiayan+Guo%2C+Ruochen+Zhao%2C+Xingxuan+Li%2C+Yuqian+Yuan%2C+Boqiang+Zhang%2C+Yuming+Jiang%2C+Yifei+Xin%2C+Ronghao+Dang%2C+et+al%2E+2024%2E+Chain+of+ideas%3A+Revolutionizing+research+via+novel+idea+devel)
17. Xiangci Li and Jessica Ouyang. 2024. Related work and citation text generation: A survey. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13846–13864, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xiangci+Li+and+Jessica+Ouyang%2E+2024%2E+Related+work+and+citation+text+generation%3A+A+survey%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+13846%E2%80%9313864%2C+)
18. Chris Lu, Cong Lu, Robert Tjarko Lange, Jakob Foerster, Jeff Clune, and David Ha. 2024. [The ai scientist: Towards fully automated open-ended scientific discovery](https://md.research.elamur.ai/free/en/papers/lu-2024-ai-scientist-fully-automated/). arXiv preprint arXiv:2408.06292.
19. Bodhisattwa Prasad Majumder, Harshit Surana, Dhruv Agarwal, Bhavana Dalvi Mishra, Abhijeetsingh Meena, Aryan Prakhar, Tirth Vora, Tushar Khot, Ashish Sabharwal, and Peter Clark. 2024. [Discoverybench: Towards data-driven discovery with large language models](https://md.research.elamur.ai/free/en/papers/majumder-2024-discoverybench-data-driven-discovery/). arXiv preprint arXiv:2407.01725.
20. Rahul Nadkarni, David Wadden, Iz Beltagy, Noah Smith, Hannaneh Hajishirzi, and Tom Hope. Scientific language models for biomedical knowledge base completion: An empirical study. In NeurIPS 2021 AI for Science Workshop. [find](https://scholar.google.com/scholar?q=Rahul+Nadkarni%2C+David+Wadden%2C+Iz+Beltagy%2C+Noah+Smith%2C+Hannaneh+Hajishirzi%2C+and+Tom+Hope%2E+Scientific+language+models+for+biomedical+knowledge+base+completion%3A+An+empirical+study%2E+In+NeurIPS+2021+AI+for)
21. Harshit Nigam, Manasi Patwardhan, Lovekesh Vig, and Gautam Shroff. 2024. An interactive co-pilot for accelerated research ideation. In Proceedings of the Third Workshop on Bridging Human–Computer Interaction and Natural Language Processing, pages 60–73. [find](https://scholar.google.com/scholar?q=Harshit+Nigam%2C+Manasi+Patwardhan%2C+Lovekesh+Vig%2C+and+Gautam+Shroff%2E+2024%2E+An+interactive+co%2Dpilot+for+accelerated+research+ideation%2E+In+Proceedings+of+the+Third+Workshop+on+Bridging+Human%E2%80%93Computer+Inte)
22. Kevin Pu, KJ Feng, Tovi Grossman, Tom Hope, Bhavana Dalvi Mishra, Matt Latzke, Jonathan Bragg, Joseph Chee Chang, and Pao Siangliulue. 2024. Ideasynth: Iterative research idea development through evolving and composing idea facets with literature-grounded feedback. arXiv preprint arXiv:2410.04025. — [arXiv:2410.04025](https://arxiv.org/abs/2410.04025) [find](https://scholar.google.com/scholar?q=Kevin+Pu%2C+KJ+Feng%2C+Tovi+Grossman%2C+Tom+Hope%2C+Bhavana+Dalvi+Mishra%2C+Matt+Latzke%2C+Jonathan+Bragg%2C+Joseph+Chee+Chang%2C+and+Pao+Siangliulue%2E+2024%2E+Ideasynth%3A+Iterative+research+idea+development+through+evol)
23. Biqing Qi, Kaiyan Zhang, Kai Tian, Haoxiang Li, Zhang-Ren Chen, Sihang Zeng, Ermo Hua, Hu Jinfang, and Bowen Zhou. 2024. [Large language models as biomedical hypothesis generators: a comprehensive evaluation](https://md.research.elamur.ai/free/en/papers/qi-2024-large-language-models-biomedical-hypothesis/). arXiv preprint arXiv:2407.08940.
24. Chenglei Si, Diyi Yang, and Tatsunori Hashimoto. 2024. [Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers](https://md.research.elamur.ai/free/en/papers/si-2024-llms-generate-novel-research/). arXiv preprint arXiv:2409.04109.
25. Hongjin SU, Jungo Kasai, Chen Henry Wu, Weijia Shi, Tianlu Wang, Jiayi Xin, Rui Zhang, Mari Ostendorf, Luke Zettlemoyer, Noah A. Smith, and Tao Yu. 2023. Selective annotation makes language models better few-shot learners. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Hongjin+SU%2C+Jungo+Kasai%2C+Chen+Henry+Wu%2C+Weijia+Shi%2C+Tianlu+Wang%2C+Jiayi+Xin%2C+Rui+Zhang%2C+Mari+Ostendorf%2C+Luke+Zettlemoyer%2C+Noah+A%2E+Smith%2C+and+Tao+Yu%2E+2023%2E+Selective+annotation+makes+language+models+bet)
26. Saatviga Sudhahar, Bugra Ozer, Jiakang Chang, Wayne Chadwick, Daniel O’Donovan, Aoife Campbell, Emma Tulip, Neil Thompson, and Ian Roberts. 2024. An experimentally validated approach to automated biological evidence generation in drug discovery using knowledge graphs. Nature Communications, 15(1):57… [find](https://scholar.google.com/scholar?q=Saatviga+Sudhahar%2C+Bugra+Ozer%2C+Jiakang+Chang%2C+Wayne+Chadwick%2C+Daniel+O%E2%80%99Donovan%2C+Aoife+Campbell%2C+Emma+Tulip%2C+Neil+Thompson%2C+and+Ian+Roberts%2E+2024%2E+An+experimentally+validated+approach+to+automated+biol)
27. Don R Swanson. 1986. Undiscovered public knowledge. The Library Quarterly, 56(2):103–118. [find](https://scholar.google.com/scholar?q=Don+R+Swanson%2E+1986%2E+Undiscovered+public+knowledge%2E+The+Library+Quarterly%2C+56%282%29%3A103%E2%80%93118%2E)
28. Justin Sybrandt, Ilya Tyagin, Michael Shtutman, and Ilya Safro. 2020. Agatha: automatic graph mining and transformer based hypothesis generation approach. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 2757–2764. [find](https://scholar.google.com/scholar?q=Justin+Sybrandt%2C+Ilya+Tyagin%2C+Michael+Shtutman%2C+and+Ilya+Safro%2E+2020%2E+Agatha%3A+automatic+graph+mining+and+transformer+based+hypothesis+generation+approach%2E+In+Proceedings+of+the+29th+ACM+International+)
29. Vikas Thada and Vivek Jaglan. 2013. Comparison of jaccard, dice, cosine similarity coefficient to find best fitness value for web retrieved documents using genetic algorithm. International Journal of Innovations in Engineering and Technology, 2(4):202–205. [find](https://scholar.google.com/scholar?q=Vikas+Thada+and+Vivek+Jaglan%2E+2013%2E+Comparison+of+jaccard%2C+dice%2C+cosine+similarity+coefficient+to+find+best+fitness+value+for+web+retrieved+documents+using+genetic+algorithm%2E+International+Journal+of+)
30. Menasha Thilakaratne, Katrina Falkner, and Thushari Atapattu. 2019. A systematic review on literature-based discovery: general overview, methodology, & statistical analysis. ACM Computing Surveys (CSUR), 52(6):1–34. [find](https://scholar.google.com/scholar?q=Menasha+Thilakaratne%2C+Katrina+Falkner%2C+and+Thushari+Atapattu%2E+2019%2E+A+systematic+review+on+literature%2Dbased+discovery%3A+general+overview%2C+methodology%2C+%26+statistical+analysis%2E+ACM+Computing+Surveys+%28CSU)
31. Byron C. Wallace, Sayantan Saha, Frank Soboczenski, and Iain J. Marshall. 2021. Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization. In Proceedings of AMIA Informatics Summit. [find](https://scholar.google.com/scholar?q=Byron+C%2E+Wallace%2C+Sayantan+Saha%2C+Frank+Soboczenski%2C+and+Iain+J%2E+Marshall%2E+2021%2E+Generating+%28Factual%3F%29+Narrative+Summaries+of+RCTs%3A+Experiments+with+Neural+Multi%2DDocument+Summarization%2E+In+Proceedings+)
32. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2023a. [Scimon: Scientific inspiration machines optimized for novelty](https://md.research.elamur.ai/free/en/papers/wang-2023-scimon-scientific-inspiration-machines/). arXiv preprint arXiv:2305.14259.
33. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2023b. [Scimon: Scientific inspiration machines optimized for novelty](https://md.research.elamur.ai/free/en/papers/wang-2023-scimon-scientific-inspiration-machines/). arXiv preprint arXiv:2305.14259.
34. Yi Xu, Shuqian Sheng, Bo Xue, Luoyi Fu, Xinbing Wang, and Chenghu Zhou. 2023. Exploring and verbalizing academic ideas by concept co-occurrence. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13001–13027. [find](https://scholar.google.com/scholar?q=Yi+Xu%2C+Shuqian+Sheng%2C+Bo+Xue%2C+Luoyi+Fu%2C+Xinbing+Wang%2C+and+Chenghu+Zhou%2E+2023%2E+Exploring+and+verbalizing+academic+ideas+by+concept+co%2Doccurrence%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+Associ)
35. Guangxu Xun, Kishlay Jha, Vishrawas Gopalakrishnan, Yaliang Li, and Aidong Zhang. 2017. Generating medical hypotheses based on evolutionary medical concepts. In 2017 IEEE International conference on data mining (ICDM), pages 535–544. IEEE. [find](https://scholar.google.com/scholar?q=Guangxu+Xun%2C+Kishlay+Jha%2C+Vishrawas+Gopalakrishnan%2C+Yaliang+Li%2C+and+Aidong+Zhang%2E+2017%2E+Generating+medical+hypotheses+based+on+evolutionary+medical+concepts%2E+In+2017+IEEE+International+conference+on+d)
36. Qian Yang, Aaron Steinfeld, and John Zimmerman. 2019. Unremarkable AI: fitting intelligent decision support into critical, clinical decision-making processes. CoRR, abs/1904.09612. — [arXiv:1904.09612](https://arxiv.org/abs/1904.09612) [find](https://scholar.google.com/scholar?q=Qian+Yang%2C+Aaron+Steinfeld%2C+and+John+Zimmerman%2E+2019%2E+Unremarkable+AI%3A+fitting+intelligent+decision+support+into+critical%2C+clinical+decision%2Dmaking+processes%2E+CoRR%2C+abs%2F1904%2E09612%2E+%E2%80%94+%5BarXiv%3A1904%2E09612)
37. Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, and Erik Cambria. 2023. [Large language models for automated open-domain scientific hypotheses discovery](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-automated/). arXiv preprint arXiv:2309.02726.
38. Yuheng Zha, Yichi Yang, Ruichen Li, and Zhiting Hu. 2023. [Alignscore: Evaluating factual consistency with a unified alignment function](https://md.research.elamur.ai/free/en/papers/zha-2023-alignscore-evaluating-factual-consistency-unified/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11328–11348.

*Updated 2 November 2026*