---
title: "Spark: A System for Scientifically Creative Idea Generation (2025)"
description: "This paper presents SPARK, a demonstration system that frames the task in terms of computational… 3 references, cited by 5 papers here."
authors: ["Aishik Sanyal", "Samuel Schapiro", "Sumuk Shashidhar", "Royce Moon", "Lav R. Varshney", "Dilek Hakkani-Tur"]
year: 2025
venue: "arXiv:2504.20090"
source: "https://arxiv.org/abs/2504.20090"
doi: "10.48550/arxiv.2504.20090"
arxiv: "2504.20090"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sanyal-2025-spark-system-scientifically-creative-idea/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sanyal-2025-spark-system-scientifically-creative-idea/)

[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/14/) / Spark: A System for Scientifically Creative Idea Generation

# Spark: A System for Scientifically Creative Idea Generation

**Authors:** Aishik Sanyal, Samuel Schapiro, Sumuk Shashidhar, Royce Moon, [Lav R. Varshney](https://md.research.elamur.ai/free/en/authors/lav-r-varshney/) and [Dilek Hakkani-Tur](https://md.research.elamur.ai/free/en/authors/dilek-hakkani-tur/) · **Year:** 2025 · **Venue:** arXiv:2504.20090 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2504.20090) · [PDF](https://arxiv.org/pdf/2504.20090) · [DOI 10.48550/arxiv.2504.20090](https://doi.org/10.48550/arxiv.2504.20090) · [arXiv 2504.20090](https://arxiv.org/abs/2504.20090) · [OpenAlex](https://openalex.org/W4417167277)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/sanyal-2025-spark-system-scientifically-creative-idea/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Research idea generation is the first step in efforts to automate science, and LLMs have recently shown they can propose novel ideas. This paper presents SPARK, a demonstration system that frames the task in terms of computational creativity (CC) principles. Its pipeline has three modules. XPLOR is a PaperQA-inspired retrieval agent that searches the literature recursively, combining embeddings, FAISS and MMR re-ranking. The Idea Generator pulls concepts and open problems from the retrieved papers and prompts an LLM to draft structured proposals, each with a plan, a title and an abstract. The Filter then has a fine-tuned reviewer model, JUDGE, write several critiques of each idea. A separate LLM reads these critiques and issues an accept or reject verdict along with a utility score. JUDGE was trained on about 600K OpenReview reviews paired with abstracts. The abstracts were rewritten to strip out claims about results, so the model judges the idea itself. The authors report that JUDGE beats its base models. They release the training dataset and outline open CC questions, such as how to judge an idea's utility before any results exist and whether AI can produce transformational ideas.

## Key points
- **Training data:** JUDGE learned from roughly 600K expert reviews harvested from OpenReview. The dataset is public as `spiralworks/openreview_wildcard_2025_v2` on Hugging Face.
- **Model sizes:** JUDGE comes in two versions, wintermute-tiny (based on Qwen-7B) and wintermute-medium (based on Qwen-72B).
  - Both were evaluated on a temporally held-out OpenReview split, using RMSE of review scores among other measures.
  - The paper claims both beat their base models and other contemporary LLMs, but the extracted text gives no numbers.
- **Retrieval:** XPLOR uses OpenAI text-embedding-3-large, FAISS, LLM relevance scoring on a 1–10 scale, and MMR re-ranking.
  - It loops, refining queries until coverage criteria are met, for example collecting a minimum of five pieces of supporting evidence drawn from more than one source.
  - It can run in interactive or autonomous mode.
- **Scale:** the pipeline has generated and filtered more than 10,000 AI-related research ideas.
- **Limitations:** the system has only been tested within AI, and each idea passes through the filter once, with no feedback loop to the generator. Retrieval relies on similarity rather than structured knowledge sources such as ontologies.

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

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,959 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,789 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,673 works · [💭 Experimental and Cognitive Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/experimental-and-cognitive-psychology/) · 950 works

## Cite

Cite as: Aishik Sanyal, Samuel Schapiro, Sumuk Shashidhar, Royce Moon, Lav R. Varshney and Dilek Hakkani-Tur. 2025. Spark: A System for Scientifically Creative Idea Generation. arXiv:2504.20090.

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

```bibtex
@misc{sanyal2025spark,
  title = {{Spark: A System for Scientifically Creative Idea Generation}},
  author = {Aishik Sanyal, Samuel Schapiro, Sumuk Shashidhar, Royce Moon, Lav R. Varshney and Dilek Hakkani-Tur},
  year = {2025},
  doi = {10.48550/arxiv.2504.20090},
  eprint = {2504.20090},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2504.20090}
}
```

- [← previous Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning](https://md.research.elamur.ai/free/en/papers/yu-2025-self-error-instruct-generalizing-errors/)
- [next → StepFun-Prover Preview: Let's Think and Verify Step by Step](https://md.research.elamur.ai/free/en/papers/shang-2025-stepfun-prover-preview-let-s/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/14/)

## References

3 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. [Boden 2004] Boden, M. A. 2004. The Creative Mind: Myths and Mechanisms. Routledge. [find](https://scholar.google.com/scholar?q=%5BBoden+2004%5D+Boden%2C+M%2E+A%2E+2004%2E+The+Creative+Mind%3A+Myths+and+Mechanisms%2E+Routledge%2E)
2. [Douze et al. 2024] Douze, M.; Guzhva, A.; Deng, C.; Johnson, J.; Szilvasy, G.; Mazaré, P.-E.; Lomeli, M.; Hosseini, L.; and Jégou, H. 2024. [The faiss library](https://md.research.elamur.ai/free/en/papers/douze-2024-faiss-library/). CoRR abs/2401.08281. [Hu et al. 2022] Hu, E. J.; Shen, Y.; Wallis, P.; Allen-Zhu, Z.; Li, Y.; Wang, S.; Wang, L.; Chen, W.; et al. 2022. L…
3. [Thagard 1988[ Thagard, P](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-automated/). 1988. Computational philosophy of science. MIT press. [Wang and Clark 2024] Wang, T., and Clark, P. 2024. Virsci: Virtual scientists for ai-driven research. In Proceedings of the AAAI Conference on Artificial Intelligence. [Wang et al. 2024] Wang, Q.; Downey, D.; Ji, H.; a…

*Updated 3 November 2026*