Elamur Research⌕
☰
home / papers / 2026 / CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation

CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation

Paper · 2026 · Noy Sternlicht and Tom Hope

Summary

Recombination, building new ideas by merging or adapting existing ones, is a central driver of scientific innovation. Until now, no large collection of real recombinations from the literature has existed. The authors frame this as a new information extraction task: find abstracts where authors explicitly say their contribution comes from either a blend of concepts or an inspiration carried from a source concept to a target. They built an expert-annotated dataset, fine-tuned an LLM extractor on it, and ran the extractor over arXiv abstracts in AI. The result is CHIMERA, a knowledge base of more than 28K recombination examples. The extractor also transferred to a biological domain.

The authors use CHIMERA in two ways:

  • Meta-science analysis. Researchers tend to borrow inspirations from other fields but blend mechanisms from within their own field.
  • Hypothesis generation. Models trained on CHIMERA predict inspirations or complementary blend elements much better on held-out data. Human judges ranked their suggestions about as helpful as the real answers.

The resource provides finer-grained signals than citation or co-occurrence methods for studying and supporting cross-disciplinary ideation.

Key points

  • Schema: There are two relation types over free-form spans. Blend links combination-elements. Inspiration runs from an inspiration-source to an inspiration-target. The schema also covers analogies, abstractions and reductions.
  • Data: The manually annotated, expert-verified dataset has 500+ abstracts, labeled by Upwork annotators paid $26–30/hour. The automatically mined KB holds over 28K recombinations.
  • Models: Extraction and prediction experiments used Mistral-7B, all-mpnet-base, GPT-4o and the PURE baseline. GPT-4o also handled auxiliary jobs such as span-similarity judging and domain labeling.
  • Human evaluation: Three experienced researchers ranked suggestions for 100 examples from six sources. The sources were the reranked method, ground truth, random, GPT-4o, ZS-CHIMERA and ZS-SciERC. The method's suggestions ranked close to ground truth and above all baselines.
  • Limitations: Extraction covers abstracts only and contains some errors, with a remaining gap to human performance. Open-ended evaluation can undercount valid suggestions as misses. Code, checkpoints and annotations are released under an open license.

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 IntelligenceSeattle · United States275 works · 97,634 citations🎓Hebrew University of JerusalemJerusalem · Israel65 works · 9,387 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksDecision Sciences · 209 worksStatistics, Probability and Uncertainty · 61 works

🧭 Topics 1Research subjects and languages the work is about.Knowledge graphs & ontologies · 192 works

Cite

Cite as Noy Sternlicht and Tom Hope. 2026. CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.85

@inproceedings{sternlicht2026chimera,
  title = {{CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation}},
  author = {Noy Sternlicht and Tom Hope},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.85},
  url = {https://doi.org/10.18653/v1/2026.acl-long.85}
}

References

50 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. 2019. The cambridge handbook of creativity. find
  2. Joel Chan, Joseph Chee Chang, Tom Hope, Dafna Shahaf, and Aniket Kittur. 2018. Solvent. Proceedings of the ACM on Human-Computer Interaction, 2:1 – 21. find
  3. Joel Chan, Katherine Fu, Christian Schunn, Jonathan Cagan, Kristin Wood, and Kenneth Kotovsky. 2011. On the benefits and pitfalls of analogies for innovative design: Ideation performance based on analogical distance, commonness, and modality of examples. Journal of mechanical design, 133(8):081004. find
  4. Lydia B. Chilton, S. Petridis, and Maneesh Agrawala. 2019. Visiblends: A flexible workflow for visual blends. Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. find
  5. DaEun Choi, Sumin Hong, Jeongeon Park, John Joon Young Chung, and Juho Kim. 2023. Creativeconnect: Supporting reference recombination for graphic design ideation with generative ai. Proceedings of the CHI Conference on Human Factors in Computing Systems. find
  6. Tom Hope, Joel Chan, Aniket Kittur, and Dafna Shahaf. 2017. Accelerating innovation through analogy mining. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’17, pages 235–243, New York, NY, USA. ACM. find
  7. DaEun Choi, Sumin Hong, Jeongeon Park, John Joon Young Chung, and Juho Kim. 2024. Creativeconnect: Supporting reference recombination for graphic design ideation with generative ai. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, pages 1–25. find
  8. J. Edward Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. ArXiv, abs/2106.09685.
  9. Rosario Delgado and Xavier-Andoni Tibau. 2019. Why cohen’s kappa should be avoided as performance measure in classification. PloS one, 14(9):e0222916. find
  10. Brian Falkenhainer, Kenneth D Forbus, and Dedre Gentner. 1989. The structure-mapping engine: Algorithm and examples. Artificial intelligence, 41(1):1– 63. find
  11. Santo Fortunato, Carl T. Bergstrom, Katy Börner, James A. Evans, Dirk Helbing, Stasa Milojevic, Alexander Michael Petersen, Filippo Radicchi, Roberta Sinatra, Brian Uzzi, Alessandro Vespignani, Ludo Waltman, Dashun Wang, and Albert Ĺaszló Barabási. 2018. Science of science. Nature, 214:1– 2. find
  12. Felix Frohnert, Xuemei Gu, Mario Krenn, and Evert P L van Nieuwenburg. 2024. Discovering emergent connections in quantum physics research via dynamic word embeddings. Machine Learning: Science and Technology, 6. find
  13. Aniketh Garikaparthi, Manasi Patwardhan, Lovekesh Vig, and Arman Cohan. 2025. Iris: Interactive research ideation system for accelerating scientific discovery. Preprint, arXiv:2504.16728. find
  14. Dedre Gentner. 1983. Structure-mapping: A theoretical framework for analogy. Cognitive science, 7(2):155– 170. find
  15. Dedre Gentner, Sarah Brem, Ron Ferguson, Philip Wolff, Arthur B Markman, and KD Forbus. 1997. Analogy and creativity in the works of johannes kepler. Creative thought: An investigation of conceptual structures and processes, pages 403–459. find
  16. Fernando Gonzalez, Zhijing Jin, Bernhard Schölkopf, Tom Hope, Mrinmaya Sachan, and Rada Mihalcea. 2023. Beyond good intentions: Reporting the research landscape of nlp for social good. arXiv preprint arXiv:2305.05471. find
  17. Moritz Hennen, Florian Babl, and Michaela Geierhos. 2024. Iter: Iterative transformer-based entity recognition and relation extraction. In Conference on Empirical Methods in Natural Language Processing. find
  18. Keith J. Holyoak and Paul Thagard. 1994. Mental leaps: Analogy in creative thought. find
  19. Fantine Huot, Reinald Kim Amplayo, Jennimaria Palomaki, Alice Shoshana Jakobovits, Elizabeth Clark, and Mirella Lapata. 2024. Agents’ room: Narrative generation through multi-step collaboration. ArXiv, abs/2410.02603. — [arXiv:2410.02603](https://arxiv.org/abs/2410.02603) find
  20. Sarthak Jain, Madeleine van Zuylen, Hannaneh Hajishirzi, and Iz Beltagy. 2020. Scirex: A challenge dataset for document-level information extraction. In Annual Meeting of the Association for Computational Linguistics.
  21. Sophie F. Jentzsch and K. Kersting. 2023. Chatgpt is fun, but it is not funny! humor is still challenging large language models. ArXiv, abs/2306.04563. find
  22. Hyeonsu B Kang, Xin Qian, Tom Hope, Dafna Shahaf, Joel Chan, and Aniket Kittur. 2022. Augmenting scientific creativity with an analogical search engine. ACM Transactions on Computer-Human Interaction, 29(6):1–36. find
  23. Uri Katz, Mosh Levy, and Yoav Goldberg. 2024. Knowledge navigator: Llm-guided browsing framework for exploratory search in scientific literature. Preprint, arXiv:2408.15836. find
  24. G. Knoblich, S. Ohlsson, H. Haider, and D. Rhenius. 1999. Constraint relaxation and chunk decomposition in insight problem solving. Journal of Experimental Psychology: Learning, Memory, and Cognition, 25(6):1534–1555. 00691. find
  25. Mario Krenn, Lorenzo Buffoni, Bruno Coutinho, Sagi Eppel, Jacob Gates Foster, Andrew Gritsevskiy, Harlin Lee, Yichao Lu, João P. Moutinho, Nima Sanjabi, Rishi Sonthalia, Ngoc M. Tran, Francisco Valente, Yangxinyu Xie, Rose Yu, and Michael Kopp. 2022. Forecasting the future of artificial intelligence… find
  26. Yi Luan, Luheng He, Mari Ostendorf, and Hannaneh Hajishirzi. 2018. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction. ArXiv, abs/1808.09602.
  27. T. McCaffrey. 2012. Innovation Relies on the Obscure: A Key to Overcoming the Classic Problem of Functional Fixedness. Psychological Science, 23(3):215– 218. 00117. find
  28. Céline McKeown. 2014. The cognitive science of science: explanation, discovery, and conceptual change. Ergonomics, 57:632 – 633. find
  29. Yan Meng, Liangming Pan, Yixin Cao, and Min-Yen Kan. 2023. Followupqg: Towards information-seeking follow-up question generation. In International Joint Conference on Natural Language Processing. find
  30. Aakanksha Naik, Bailey Kuehl, Erin Bransom, Doug Downey, and Tom Hope. 2024. Care: Extracting experimental findings from clinical literature. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4580–4596. find
  31. Huitong Pan, Qi Zhang, Cornelia Caragea, Eduard Constantin Dragut, and Longin Jan Latecki. 2024. Scidmt: A large-scale corpus for detecting scientific mentions. In International Conference on Language Resources and Evaluation. find
  32. Tal Perry. 2021. Lighttag: Text annotation platform. In Conference on Empirical Methods in Natural Language Processing. find
  33. Aniket Pramanick, Yufang Hou, Saif M. Mohammad, and Iryna Gurevych. 2025. The nature of NLP: Analyzing contributions in NLP papers. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25169–25191, Vienna, Austria. Association for…
  34. Marissa Radensky, Simra Shahid, Raymond Fok, Pao Siangliulue, Daniel S Weld, and Tom Hope. 2024. Scideator: Human-llm scientific idea generation grounded in research-paper facet recombination. arXiv preprint arXiv:2409.14634. from distant disciplines. Nature Communications, 14. — [arXiv:2409.14634](https://arxiv.org/abs/2409.14634) find
  35. Chenglei Si, Diyi Yang, and Tatsunori Hashimoto. 2024. Can llms generate novel research ideas? a large-scale human study with 100+ nlp researchers. arXiv preprint arXiv:2409.04109.
  36. Daniel N Sosa and Russ B Altman. 2022. Contexts and contradictions: a roadmap for computational drug repurposing with knowledge inference. Briefings in bioinformatics, 23(4):bbac268. find
  37. Arvind Srinivasan and Joel Chan. 2024. Improving selection of analogical inspirations through chunking and recombination. Proceedings of the 16th Conference on Creativity & Cognition. find
  38. Sangho Suh, Meng Chen, Bryan Min, Toby Jia-Jun Li, and Haijun Xia. 2023. Luminate: Structured generation and exploration of design space with large language models for human-ai co-creation. Proceedings of the CHI Conference on Human Factors in Computing Systems. find
  39. Weiwei Sun, Lingyong Yan, Xinyu Ma, Pengjie Ren, Dawei Yin, and Zhaochun Ren. 2023. Is chatgpt good at search? investigating large language models as re-ranking agent. ArXiv, abs/2304.09542.
  40. You Can Teach, Daniel Ruffinelli, Samuel Broscheit, and Rainer Gemulla. 2020. You can teach an old dog new tricks! on training knowledge graph embeddings. In International Conference on Learning Representations. find
  41. Brian Uzzi, Satyam Mukherjee, Michael Stringer, and Ben Jones. 2013. Atypical combinations and scientific impact. Science, 342(6157):468–472. find
  42. Tarek Saier and Michael Färber. 2020. unarxive: a large scholarly data set with publications’ full-text, annotated in-text citations, and links to metadata. Scientometrics, 125:3085 – 3108. find
  43. Jan Philip Wahle, Terry Ruas, Mohamed Abdalla, Bela Gipp, and Saif Mohammad. 2023. We are who we cite: Bridges of influence between natural language processing and other academic fields. ArXiv, abs/2310.14870. find
  44. Oscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier López de Lacalle, German Rigau, and Eneko Agirre. 2023. Gollie: Annotation guidelines improve zero-shot information-extraction. ArXiv, abs/2310.03668.
  45. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533.
  46. Omar Sharif, Joseph Gatto, Madhusudan Basak, and Sarah Masud Preum. 2024. Explicit, implicit, and scattered: Revisiting event extraction to capture complex arguments. In Conference on Empirical Methods in Natural Language Processing. find
  47. Qingyun Wang, Doug Downey, Heng Ji, and Tom Hope. 2024. Scimon: Scientific inspiration machines optimized for novelty. ACL. find
  48. Feng Shi and James Evans. 2023. Surprising combinations of research contents and contexts are related to impact and emerge with scientific outsiders from distant disciplines. Nature Communications, 14(1):1641. find
  49. Feng Shi and James Allen Evans. 2019. Surprising combinations of research contents and contexts are related to impact and emerge with scientific outsiders Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting el… find
  50. Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighoff. 2023. C-pack: Packaged resources to advance general chinese embedding. Preprint, arXiv:2309.07597.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/sternlicht-2026-chimera-knowledge-base-scientific-idea/