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

arXiv: https://arxiv.org/abs/2505.20779 · HTML: https://mlsanity.com/paper/2505.20779/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 59 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 27 of 27)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction](https://mlsanity.com/paper/1808.09602/) (2018)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction](https://mlsanity.com/paper/2310.03668/) (2023)
- [SciREX: A Challenge Dataset for Document-Level Information Extraction](https://mlsanity.com/paper/2005.00512/) (2020)
- [Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation](https://mlsanity.com/paper/2310.12953/) (2023)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network](https://mlsanity.com/paper/2210.00881/) (2022)
- [CreativeConnect: Supporting Reference Recombination for Graphic Design Ideation with Generative AI](https://mlsanity.com/paper/2312.11949/) (2023)
- [Accelerating Innovation Through Analogy Mining](https://mlsanity.com/paper/1706.05585/) (2017)
- [Augmenting Scientific Creativity with an Analogical Search Engine](https://mlsanity.com/paper/2205.15476/) (2022)
- [We are Who We Cite: Bridges of Influence Between Natural Language Processing and Other Academic Fields](https://mlsanity.com/paper/2310.14870/) (2023)
- [MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows](https://mlsanity.com/paper/2406.06357/) (2024)
- [Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature](https://mlsanity.com/paper/2408.15836/) (2024)
- [LightTag: Text Annotation Platform](https://mlsanity.com/paper/2109.02320/) (2021)
- [MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search](https://mlsanity.com/paper/2505.19209/) (2025)
- [FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generation](https://mlsanity.com/paper/2309.05007/) (2023)
- [The Nature of NLP: Analyzing Contributions in NLP Papers](https://mlsanity.com/paper/2409.19505/) (2024)
- [Invention as a Combinatorial Process: Evidence from U.S. Patents](https://mlsanity.com/paper/1406.2938/) (2014)
- [Explicit, Implicit, and Scattered: Revisiting Event Extraction to Capture Complex Arguments](https://mlsanity.com/paper/2410.03594/) (2024)
- [Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good](https://mlsanity.com/paper/2305.05471/) (2023)
- [SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions](https://mlsanity.com/paper/2406.14756/) (2024)
- [CARE: Extracting Experimental Findings From Clinical Literature](https://mlsanity.com/paper/2311.09736/) (2023)
- [Discovering emergent connections in quantum physics research via dynamic word embeddings](https://mlsanity.com/paper/2411.06577/) (2024)

## Built on by (most cited first, 6 of 6)

- [The Ramon Llull's Thinking Machine for Automated Ideation](https://mlsanity.com/paper/2508.19200/) (2025)
- [Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts](https://mlsanity.com/paper/2606.09105/) (2026)
- [TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval](https://mlsanity.com/paper/2607.28498/) (2026)
- [Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure](https://mlsanity.com/paper/2608.20361/) (2026)
- [RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature](https://mlsanity.com/paper/2608.27394/) (2026)
- [Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational Fingerprints](https://mlsanity.com/paper/2609.07595/) (2026)

## Abstract (arXiv)

A hallmark of human innovation is recombination -- the creation of novel ideas by integrating elements from existing concepts and mechanisms. In this work, we introduce CHIMERA, the first large-scale Knowledge Base (KB) of recombination examples automatically mined from the scientific literature. CHIMERA enables empirical analysis of how scientists recombine concepts and draw inspiration from different areas, and enables training models that propose cross-disciplinary research directions. To construct this KB, we define a new information extraction task: identifying recombination instances in papers. We curate an expert-annotated dataset and use it to fine-tune an LLM-based extraction model, which we apply to a broad corpus of AI papers. We also demonstrate generalization to a biological domain. We showcase the utility of CHIMERA through two applications. First, we analyze patterns of recombination across AI subfields. Second, we train a scientific hypothesis generation model using the KB, showing that it can propose directions that researchers rate as inspiring.