TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval
Scientific hypothesis generation for AI for Science typically involves Scientific Inspiration Retrieval (SIR) followed by hypothesis composition. Existing SIR methods rank papers by topical similarity and do not explicitly represent how a candidate inspiration transfers to a target problem. This is especially limiting for remote inspirations, whose value often lies in reusable problem-solving principles rather than topical overlap. Motivated by how humans abstract transferable aspects of a source and remap them to a new target, we reformulate SIR as target-conditioned abstraction (TCA). The retrieval object is a transferable abstract principle extracted from a candidate specifically for the target. We present TCA-SIR, which learns to generate target-conditioned abstractions and uses their representations to predict transferability. On ResearchBench, TCA-SIR outperforms prior SIR methods and direct LLM retrieval, improving HitRate@top4% over MOOSE-Chem by more than 10 percentage points. Learned abstractions also recover target-relevant mechanisms more clearly than an untrained TCA prompt, yielding both stronger retrieval and an interpretable rationale for scientific inspiration.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
Retrieved scientific literature can serve as inspiration for both human and AI scientists. Inspiration can take different forms: prior work may directly suggest how to address a problem, or surface directions at differen…
ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
Large language models (LLMs) have demonstrated potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark. To ad…
Benchmarkingscientific discoveryGraph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation
Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the generated results often lack controllable academic context and traceable inspiration pathways. To bridge this ga…
Reinforcement LearningKnowledge GraphsSciMON: Scientific Inspiration Machines Optimized for Novelty
We explore and enhance the ability of neural language models to generate novel scientific directions grounded in literature. Work on literature-based hypothesis generation has traditionally focused on binary link predict…
Contextualized Literature-based DiscoveryLink PredictionRetrievalMOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses
Scientific discovery plays a pivotal role in advancing human society, and recent progress in large language models (LLMs) suggests their potential to accelerate this process. However, it remains unclear whether LLMs can …
scientific discoveryvalid