Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?

• URL: http://arxiv.org/abs/2605.27082v1
• Date: Tue, 26 May 2026 14:33:03 GMT
• Title: Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
• Abstract summary: We propose SCENE, a bi-level multi-agent framework that treats knowledge contextualization as iterative search.<n>In clinical trials, SCENE discovers specific, well-supported subgroups and outperforms existing baselines.<n>These results show that SCENE bridges broad knowledge and scenario-specific evidence, producing traceable, inspectable hypotheses for follow-up validation.
• Score: 20.421741889749573
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Biomedical discovery often requires connecting broad biomedical knowledge with specific experimental or clinical data. Background knowledge suggests relevant mechanisms but is usually too general to map directly onto dataset variables, while data-driven patterns can be dataset-specific and hard to interpret mechanistically. We study this missing link as knowledge contextualization: transforming broad biomedical knowledge into evidence-supported, scenario-grounded propositions that domain experts can inspect, replay, and validate. We propose SCENE, a bi-level multi-agent framework that treats knowledge contextualization as iterative search. The upper level converts broad knowledge into search directions and grounds them in the dataset schema. The lower level executes these directions through multi-objective optimization to identify concrete propositions that balance evidential strength and data support. Feedback between the two levels progressively refines the search. We evaluate SCENE in two settings: discovering patient subgroups with heterogeneous treatment benefits in clinical trial scenarios, and identifying context-specific biological responses in LINCS L1000 studies. In clinical trials, SCENE discovers specific, well-supported subgroups and outperforms existing baselines. In L1000 studies, SCENE identifies perturbational contexts with strong target-response matching and high positive rates. These results show that SCENE bridges broad knowledge and scenario-specific evidence, producing traceable, inspectable hypotheses for follow-up validation.

Related papers

• LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations [1.6926314031847856]
  We present LatentVerse, a representation analysis resource that combines a report-driven exploration with a command-line interface for scalable technical exploration.<n>LatentVerse unifies diagnostics for various representation quality metrics and extends to multimodal settings by embeddings into shared and modality-specific components.<n>We evaluate LatentVerse through controlled unimodal and multimodal simulations, discovery-oriented analyses on real biomedical embeddings, and a user study across diverse use cases.
  arXiv  Detail & Related papers  (2026-09-11T02:34:29Z)
• DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing [55.45112712244231]
  DrugReason is a multi-view reasoning framework that integrates grounded KG reasoning with LLM-generated mechanistic inference for drug repurposing.<n> Experiments on PharmaDB, DDInter, and DrugBank show that DrugReason improves average performance over strong single-view reasoning baselines.
  arXiv  Detail & Related papers  (2026-09-06T18:54:26Z)
• DeepEvidence: Empowering Biomedical Discovery with Deep Knowledge Graph Research [33.51246292480848]
  We introduce DeepEvidence, an AI-agent framework designed to perform Deep Research across various biomedical knowledge graphs (KGs)<n>Unlike generic Deep Research systems that rely primarily on internet-scale text, DeepEvidence incorporates specialized knowledge-graph tooling and coordinated exploration strategies.<n>DeepEvidence demonstrates substantial gains in systematic exploration and evidence synthesis across four key stages of the biomedical discovery lifecycle.
  arXiv  Detail & Related papers  (2025-12-23T14:34:38Z)
• Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes [13.564947974902429]
  We propose CLOZE, a novel framework that uses large language models (LLMs) to automatically extract medical entities from clinical notes.<n>By capitalizing on the strong language understanding and extensive knowledge of pre-trained LLMs, CLOZE effectively identifies disease-related concepts and captures complex hierarchical relationships.
  arXiv  Detail & Related papers  (2025-11-20T17:00:46Z)
• Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models [51.91760712805404]
  We introduce VivaBench, a benchmark for evaluating sequential clinical reasoning in large language models (LLMs)<n>Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training.<n>Our analysis identified several failure modes that mirror common cognitive errors in clinical practice.
  arXiv  Detail & Related papers  (2025-10-11T16:24:35Z)
• Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents [52.50038914857797]
  We term this process hypothesis hunting: the cumulative search for insight through sustained exploration across vast and complex hypothesis spaces.<n>We introduce AScience, a framework modeling discovery as the interaction of agents, networks, and evaluation norms, and implement it as ASCollab.<n> Experiments show that such social dynamics enable the accumulation of expert-rated results along the diversity-quality-novelty frontier.
  arXiv  Detail & Related papers  (2025-10-08T08:47:07Z)
• ChatEXAONEPath: An Expert-level Multimodal Large Language Model for Histopathology Using Whole Slide Images [19.661619004001654]
  We introduce an expert-level MLLM for histopathology using WSIs, dubbed as ChatEXAONEPath.<n>We demonstrate the ability of diagnosing the given histopathology images using ChatEXAONEPath with the acceptance rate of 62.9%.<n>Our proposed model can understand pan-cancer WSIs and clinical context from various cancer types.
  arXiv  Detail & Related papers  (2025-04-17T15:33:17Z)
• 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)
• Enhancing Biomedical Knowledge Discovery for Diseases: An Open-Source Framework Applied on Rett Syndrome and Alzheimer's Disease [28.68816381566995]
  We introduce an open-source framework designed to construct knowledge around specific diseases directly from raw text.<n>To facilitate research in disease-related knowledge discovery, we create two annotated datasets focused on Rett syndrome and Alzheimer's disease.
  arXiv  Detail & Related papers  (2024-07-18T13:20:53Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation [0.0]
  This work explores the potential of Large Language Models for dialoguing with biomedical background knowledge. The framework involves of three evaluation steps, each assessing different aspects sequentially: fluency, prompt alignment, semantic coherence, factual knowledge, and specificity of the generated responses. The work provides a systematic assessment on the ability of eleven state-of-the-art models LLMs, including ChatGPT, GPT-4 and Llama 2, in two prompting-based tasks.
  arXiv  Detail & Related papers  (2023-05-28T22:46:21Z)
• Informing clinical assessment by contextualizing post-hoc explanations of risk prediction models in type-2 diabetes [50.8044927215346]
  We consider a comorbidity risk prediction scenario and focus on contexts regarding the patients clinical state. We employ several state-of-the-art LLMs to present contexts around risk prediction model inferences and evaluate their acceptability. Our paper is one of the first end-to-end analyses identifying the feasibility and benefits of contextual explanations in a real-world clinical use case.
  arXiv  Detail & Related papers  (2023-02-11T18:07:11Z)

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.