paper-with-me

Papers

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition

2025-03-27 · Yujie Liu, Zonglin Yang, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, Dongzhan Zhou

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 address this gap, we introduce the first large-scale benchmark for evaluating LLMs with a near-sufficient set of sub-tasks of scientific discovery: inspiration retrieval, hypothesis composition, and hypothesis ranking. We develop an automated framework that extracts critical components - research questions, background surveys, inspirations, and hypotheses - from scientific papers across 12 disciplines, with expert validation confirming its accuracy. To prevent data contamination, we focus exclusively on papers published in 2024, ensuring minimal overlap with LLM pretraining data. Our evaluation reveals that LLMs perform well in retrieving inspirations, an out-of-distribution task, suggesting their ability to surface novel knowledge associations. This positions LLMs as "research hypothesis mines", capable of facilitating automated scientific discovery by generating innovative hypotheses at scale with minimal human intervention.

📄 PDF Abstract BibTeX arXiv:2503.21248

Code (0)

등록된 구현이 없습니다.

Tasks

Benchmarkingscientific discovery

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Focus 설명 없음

Similar Papers 제목 키워드 기반

AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

2026-04-28 · Lei Xiong, Kun Luo, Ziyi Xia, Wenbo Zhang 외 arxiv

Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a resear…

TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval

2026-07-30 · Yuto Suzuki, Farnoush Banaei-Kashani arxiv

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 explicit…

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

2024-10-09 · Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie 외

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

ResearchTown: Simulator of Human Research Community

2024-12-23 · Haofei Yu, Zhaochen Hong, Zirui Cheng, Kunlun Zhu 외

Large Language Models (LLMs) have demonstrated remarkable potential in scientific domains, yet a fundamental question remains unanswered: Can we simulate human research communities with LLMs? Addressing this question can…

Spacer: Towards Engineered Scientific Inspiration

2025-08-25 · Minhyeong Lee, Suyoung Hwang, Seunghyun Moon, Geonho Nah 외 arxiv

Recent advances in LLMs have made automated scientific research the next frontline in the path to artificial superintelligence. However, these systems are bound either to tasks of narrow scope or the limited creative cap…