Abstract Research in scientific domains now generates more than a million articles annually, overwhelming researchers and hindering discovery. This surge has sparked interest in biomedical hypothesis generation (HG), which aims to uncover implicit patterns among biomedical concepts. Most existing methods focus on pairwise link prediction, overlooking the complex, multi-concept relationships underlying many breakthroughs. We introduce HyHG , a temporal Hy pergraph contrastive learning framework for biomedical H ypothesis G eneration, which redefines hypotheses as hyperedges—sets of co-mentioned concepts in an article. By representing articles as hyperedges and organizing them into a temporal hypergraph, HyHG captures the evolution of scientific ideas over time. A transformer-based architecture learns from historical hyperedge sequences to predict future hyperedges—sets of concepts likely to co-occur in the future literature. To distinguish genuine hypotheses from misleading ones, HyHG employs a time-anchored contrastive loss and hard negative sampling based on minimal edits to real hyperedges. We demonstrate that HyHG achieves state-of-the-art performance on three biomedical datasets. Our code and data are available at: https://github.com/amir-hassan25/Temporal-Hypergraph-Contrastive-Learning.

Biomedical research now generates more than a million articles annually, overwhelming researchers and hindering discovery. This surge has sparked interest in biomedical hypothesis generation (HG), which aims to uncover implicit patterns among biomedical concepts. Most existing methods focus on pairwise link prediction, overlooking the complex, multi-concept relationships underlying many breakthroughs. We introduce HyHG, a temporal Hypergraph contrastive learning framework for biomedical Hypothesis Generation, which redefines hypotheses as hyperedges–sets of co-mentioned concepts in an article. By representing articles as hyperedges and organizing them into a temporal hypergraph, HyHG captures the evolution of scientific ideas over time. A transformer-based architecture learns from historical hyperedge sequences to predict future hyperedges–sets of concepts likely to co-occur in future literature. To distinguish genuine hypotheses from misleading ones, HyHG employs a timeanchored contrastive loss and hard negative sampling based on minimal edits to real hyperedges. We demonstrate state-of-the-art performance on three biomedical datasets. Our code and data are available at: https://github.com/amirhassan25/Temporal-Hypergraph-Contrastive-Learning.

Large language models (LLMs) have shown significant potential in scientific disciplines such as biomedicine, particularly in hypothesis generation, where they can analyze vast literature, identify patterns, and suggest research directions. However, a key challenge lies in evaluating the truthfulness of generated hypotheses, as verifying their accuracy often requires substantial time and resources. Additionally, the hallucination problem in LLMs can lead to the generation of hypotheses that appear plausible but are ultimately incorrect, undermining their reliability. To facilitate the systematic study of these challenges, we introduce TruthHypo, a benchmark for assessing the capabilities of LLMs in generating truthful scientific hypotheses, and KnowHD, a knowledge-based hallucination detector to evaluate how well hypotheses are grounded in existing knowledge. Our results show that LLMs struggle to generate truthful hypotheses. By analyzing hallucinations in reasoning steps, we demonstrate that the groundedness scores provided by KnowHD serve as an effective metric for filtering truthful hypotheses from the diverse outputs of LLMs. Human evaluations further validate the utility of KnowHD in identifying truthful hypotheses and accelerating scientific discovery. Our data and source code are available at https://github.com/Teddy-XiongGZ/TruthHypo.

Large Language Models (LLMs) have revolutionized interactions between human and artificial intelligence (AI) systems, demonstrating state-of-the-art performance across various domains, including scientific discovery and hypothesis generation. However, the absence of a comprehensive and systematic evaluation framework for LLM-driven research idea generation hinders a rigorous understanding of their strengths and limitations. To address this gap, we propose IdeaBench, a benchmark system that provides a structured dataset and evaluation framework for standardizing the assessment of research idea generation by LLMs. Our dataset comprises titles and abstracts from 2,374 influential papers across eight research domains, along with their 29,408 referenced works, creating a context-rich environment that mirrors human researchers' ideation processes. By profiling LLMs as domain-specific researchers and grounding them in similar contextual constraints, we directly leverage the models' knowledge learned from the pre-training stage to generate new research ideas. To systematically evaluate LLMs' research ideation capability and approximate human assessment, we propose a reference-based metric that aligns with human judgment to quantify idea quality with the assistance of LLMs. Through this evaluation, we find that while LLMs excel at generating novel ideas, they may struggle with generating feasible ideas. IdeaBench serves as a critical resource for benchmarking and comparing LLMs, ultimately advancing research on AI's role in automating scientific discovery.

MOTIVATION: Hypothesis generation is a fundamental problem in biomedical text mining that aims to generate ideas that are new, interesting, and plausible by discovering unexplored links between biomedical concepts. Despite significant advances made by existing approaches, they do not fully leverage the evolutionary properties of biomedical concepts. This is limiting because scientific knowledge continually evolves over time, with new facts being added and old ones becoming obsolete. Thus, it is crucial to capture the evolutionary properties of biomedical concepts from multiple perspectives (e.g. spatial, temporal, and semantic) to generate hypotheses that reflect the up-to-date information landscape of the biomedical domain. RESULTS: We introduce a novel framework, ConceptDrift, that models the hypothesis generation task as a sequence of temporal graphlets and simultaneously encodes spatial, temporal, and semantic change. Unlike existing approaches that treat these dimensions independently, ConceptDrift is the first to provide a holistic understanding of concept evolution by integrating them into a unified framework. Grounded in the theories of the Distributional Hypothesis and Conceptual Change, our method adapts these principles to the unique challenges of large-scale biomedical literature. We conduct extensive experiments across multiple datasets and demonstrate that ConceptDrift consistently outperforms state-of-the-art baselines in generating accurate and meaningful hypotheses. Our framework shows immediate practical benefits for web-based literature mining tools in life sciences and biomedicine, offering more robust and predictive feature representations. AVAILABILITY AND IMPLEMENTATION: https://github.com/amir-hassan25/ConceptDrift (DOI: 10.6084/m9.figshare.29975476).

Machine learning foundation models, particularly large language models (LLMs) such as GPT-4o, have revolutionized traditional applications in computer vision and natural language processing, marking a significant shift in recent years. Building on these advancements, recent efforts have explored the potential of foundation models in hypothesis generation, highlighting their possibility in aiding human researchers in scientific discovery. In this paper, we envision a future where academia increasingly integrates foundation models to accelerate and enhance the process of scientific discovery. Motivated by potential application scenarios of foundation models in scientific research, our vision is anchored in a central question: How can we accelerate scientific discovery with the aid of foundation models? To address this overarching question, we raise two key challenges that need to be addressed: (1) how to effectively harness the parametric knowledge embedded in foundation models to propel scientific discovery? and (2) how to develop rigorous yet scalable methods to evaluate the effectiveness of foundation models in supporting scientific research? To tackle these two challenges, we propose our approaches, termed knowledge-grounded Chain-of-Idea (KG-CoI) hypothesis generation and IdeaBench - Benchmarking LLM hypothesis generators in a customizable manner. Through addressing these challenges, we outline our vision in hope to inspire new ideas and innovations in harnessing foundation models for advancing scientific discovery, paving the way for a new era of research collaboration between humans and artificial intelligence.