HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledge

• URL: http://arxiv.org/abs/2609.12260v1
• Date: Thu, 10 Sep 2026 22:36:02 GMT
• Title: HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledge
• Abstract summary: Large language models (LLMs) can generate biomedical hypotheses, but it remains unclear whether they truly reason from scientific evidence or simply produce convincing-sounding ideas.<n>We combine three major biological databases into a unified biochemical knowledge graph and construct a benchmark of 550 paths connecting sources enzyme rare disease endpoints.<n>We find that models given both the source and disease endpoint often produce the highest-scoring hypotheses, showing that LLMs can generate compelling ideas from minimal information.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) can generate biomedical hypotheses, but it remains unclear whether they truly reason from scientific evidence or simply produce convincing-sounding ideas. To study this, we combine three major biological databases: the Kyoto Encyclopedia of Genes and Genomes (KEGG), Rhea, and UniProt, into a unified biochemical knowledge graph and construct a benchmark of 550 paths connecting enzyme sources to rare disease endpoints, yielding 13,200 hypotheses from six LLMs under four conditions varying the biological information each model receives: source enzyme only, full biological path, or source and disease endpoint only. Hypotheses are scored using an expert-derived five-criterion rubric on a 1-5 scale per criterion. We find that models given both the source and disease endpoint often produce the highest-scoring hypotheses, showing that LLMs can generate compelling ideas from minimal information. However, these hypotheses are less grounded in the evidence. In contrast, models given the full biological path generate hypotheses more consistent with known mechanistic relationships. We call this evidence-disciplined reasoning. To confirm this effect, we shuffled intermediate path steps while keeping endpoints fixed. Evidence grounding dropped significantly (delta = -0.793, p < 0.001), confirming models genuinely used path structure during reasoning. Our findings show that knowledge graphs support hypothesis generation in two ways: they identify biological endpoint pairs absent from the literature, and their mechanistic paths guide how LLMs reason between them.

Related papers

• HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses [35.57672494910454]
  How different forms of agent collaboration affect hypothesis quality remains an open question.<n>We introduce HypoEvolve, which makes collaboration explicit through successive updates to a hypothesis population.<n>Each generation specifies how scientific judgments and new proposals reshape the population, making collaboration effects on hypothesis quality directly testable.
  arXiv  Detail & Related papers  (2026-09-14T17:44:49Z)
• HyGRAIL: Cost-Aware and Evidence-Grounded Scientific Hypothesis Discovery over Knowledge Graphs [27.213223725307106]
  HyGRAIL is a cost-aware framework that combines graph neural networks with hypothesis review.<n>It retrieves node-level associations and multi-hop relational paths from the knowledge graph (KG)<n>On MatKG, HyGRAIL achieves the best F1 score of 0.429, improving over the strongest prior baseline by 0.242 F1 points and over the GNN-only baseline by 0.322.
  arXiv  Detail & Related papers  (2026-09-02T03:34:21Z)
• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning [103.788281428856]
  We introduce SciReasoner, a scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals.<n>SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary.<n>Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks.
  arXiv  Detail & Related papers  (2026-07-08T17:59:59Z)
• BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model [12.528834366422466]
  BioReason learns to produce logical, biologically coherent deductions.<n>It boosts KEGG-based disease pathway prediction accuracy from 86% to 98%.<n>It also improves variant effect prediction by an average of 15% over strong baselines.
  arXiv  Detail & Related papers  (2025-05-29T15:49:27Z)
• Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models [18.850296587858946]
  We introduce TruthHypo, a benchmark for assessing the capabilities of large language models in generating truthful hypotheses.<n>KnowHD is a knowledge-based hallucination detector to evaluate how well hypotheses are grounded in existing knowledge.
  arXiv  Detail & Related papers  (2025-05-20T16:49:40Z)
• HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation [24.656083479331645]
  We introduce HypoBench, a novel benchmark designed to evaluate hypothesis generation methods across multiple aspects.<n>We evaluate four state-of-the-art LLMs combined with six existing hypothesis-generation methods.<n>Results indicate that there is still significant room for improvement, as current hypothesis generation methods do not fully uncover all relevant or meaningful patterns.
  arXiv  Detail & Related papers  (2025-04-15T18:00:00Z)
• BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning [49.487327661584686]
  We introduce BioMaze, a dataset with 5.1K complex pathway problems from real research.<n>Our evaluation of methods such as CoT and graph-augmented reasoning, shows that LLMs struggle with pathway reasoning.<n>To address this, we propose PathSeeker, an LLM agent that enhances reasoning through interactive subgraph-based navigation.
  arXiv  Detail & Related papers  (2025-02-23T17:38:10Z)
• Causal Representation Learning from Multimodal Biomedical Observations [57.00712157758845]
  We develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biomedical datasets.<n>Key theoretical contribution is the structural sparsity of causal connections between modalities.<n>Results on a real-world human phenotype dataset are consistent with established biomedical research.
  arXiv  Detail & Related papers  (2024-11-10T16:40:27Z)
• MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses [95.25947149100533]
  It remains unclear whether large language models (LLMs) can autonomously generate novel and valid hypotheses in chemistry.<n>We develop a benchmark of 51 high-impact chemistry papers published and online after January 2024, each manually annotated by PhD chemists with background, inspirations, and hypothesis.<n>We assume that LLMs may already encode latent scientific knowledge associations not yet recognized by humans.
  arXiv  Detail & Related papers  (2024-10-09T17:19:58Z)
• Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables [49.31233968546582]
  We introduce a novel benchmark where the objective is to complete a partial causal graph.<n>We show the strong ability of LLMs to hypothesize the backdoor variables between a cause and its effect.<n>Unlike simple memorization of fixed associations, our task requires the LLM to reason according to the context of the entire graph.
  arXiv  Detail & Related papers  (2024-09-04T10:37:44Z)
• Evaluating the Potential of Leading Large Language Models in Reasoning Biology Questions [33.81650223615028]
  This study evaluated the capabilities of leading Large Language Models (LLMs) in answering conceptual biology questions. The models were tested on a 108-question multiple-choice exam covering biology topics in molecular biology, biological techniques, metabolic engineering, and synthetic biology. The results indicated GPT-4's proficiency in logical reasoning and its potential to aid biology research through capabilities like data analysis, hypothesis generation, and knowledge integration.
  arXiv  Detail & Related papers  (2023-11-05T03:34:17Z)
• Large Language Models for Automated Open-domain Scientific Hypotheses Discovery [50.40483334131271]
  This work proposes the first dataset for social science academic hypotheses discovery. Unlike previous settings, the new dataset requires (1) using open-domain data (raw web corpus) as observations; and (2) proposing hypotheses even new to humanity. A multi- module framework is developed for the task, including three different feedback mechanisms to boost performance.
  arXiv  Detail & Related papers  (2023-09-06T05:19:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.