Quantitative Evidence Mining for Plausibility-Aware Biomedical AI

• URL: http://arxiv.org/abs/2608.30393v1
• Date: Mon, 31 Aug 2026 07:48:25 GMT
• Title: Quantitative Evidence Mining for Plausibility-Aware Biomedical AI
• Abstract summary: We argue for a shift toward quantitative evidence mining.<n>We outline a framework for plausibility-aware AI that treats extracted claims as auditable evidence objects.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Biomedical artificial intelligence (AI) systems increasingly extract, organize, and reuse scientific claims from literature, clinical trials, and regulatory documents. But automatic extraction alone does not make a claim reliable evidence: a claim becomes useful only when it can be traced to its source, linked to the quantitative details that support it, and read within its biomedical context and uncertainty. This matters as large language models (LLMs) and increasingly autonomous systems drive evidence synthesis, knowledge graph (KG) construction, and decision support. Many text-mining and LLM pipelines remain relation-centric: they capture entities and relations such as Drug--TREATS--Disease, but drop the dose, effect size, population, comparator, uncertainty, and conditions under which a claim holds. Such relations can look actionable yet remain hard to verify, compare, or reuse. In this perspective, we argue for a shift toward quantitative evidence mining---extracting values, units, measured entities and properties, context, uncertainty, provenance, and plausibility as structured evidence units that populate evidence-aware KGs and can be checked for source grounding, unit consistency, completeness, and biological plausibility. We outline a framework for plausibility-aware AI that treats extracted claims not as final answers but as auditable evidence objects, making clear what was measured, how much it changed, in which setting, with what uncertainty, and from which source. The central risk is not only incorrect extraction, but claims that look like evidence while lacking the structure needed to trust them.

Related papers

• EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards [73.12811119273206]
  We introduce EarthVerse, a benchmark that evaluates scientific agents through package-scoped investigations.<n>Agents inspect heterogeneous event packages, choose compatible evidence, execute transparent calculations, reconcile source differences, and preserve provenance in the final answer.<n>Across systems, the best mean answer-unit accuracy is 84.65%, while the highest Strict@95 is only 34.81%.
  arXiv  Detail & Related papers  (2026-08-24T17:29:16Z)
• HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research [52.87128503345243]
  We introduce HiEviDR-Bench, a benchmark for evaluating Hierarchical Evidence Aggregation in Deep Research.<n>HiEviDR-Bench represents each instance with an explicit evidence graph that captures evidence selection, cross-source linking, and aggregation.<n>We develop a traceability-oriented evaluation framework with five dimensions: report quality, evidence traceability, citation accuracy, claim verification, and answer correctness.
  arXiv  Detail & Related papers  (2026-07-27T23:50:46Z)
• SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding [63.71245376513854]
  We present SciLens, an evidence-conditioned atomic entailment framework for multimodal scientific claim verification.<n>SciLens decomposes each claim into central empirical atoms and background atoms, grounds the central atoms to modality-specific evidence witnesses, and predicts the final label.<n>For tables, atoms are grounded to rows, columns, cells, arithmetic relations, and table scope; for figures, they are grounded through panels, axes, legends, visual encodings, categories, trends, ranks, and qualifier checks.
  arXiv  Detail & Related papers  (2026-06-18T19:02:17Z)
• BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering [28.39203052317792]
  BELIEF is a structured evidence modeling and uncertainty-aware fusion framework for biomedical question answering.<n>It converts retrieved documents into evidence objects that record clinical attributes, source quality, question relevance, support strength, and the associated candidate hypothesis.<n>BelIEF improves retrieved-evidence utilization by making evidence structure, path disagreement, and decision uncertainty explicit.
  arXiv  Detail & Related papers  (2026-05-17T12:58:55Z)
• CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era [51.63024682584688]
  Large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications.<n>We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing.<n>Our framework significantly outperforms prior methods in both accuracy and interpretability.
  arXiv  Detail & Related papers  (2026-02-26T19:17:39Z)
• Contradiction to Consensus: Dual Perspective, Multi Source Retrieval Based Claim Verification with Source Level Disagreement using LLM [0.17188280334580197]
  Claim verification, a.k.a. fact-checking, can help identify potential misinformation.<n>Most automated claim verification systems depend on a single knowledge source.<n>We present a novel system for open-domain claim verification.
  arXiv  Detail & Related papers  (2026-02-21T02:21:31Z)
• Combating Biomedical Misinformation through Multi-modal Claim Detection and Evidence-based Verification [11.555285143713315]
  CER (Combining Evidence and Reasoning) is a novel framework for biomedical fact-checking.<n>It integrates scientific evidence retrieval, reasoning via large language models, and supervised veracity prediction.<n>It effectively mitigates the risk of hallucinations, ensuring that generated outputs are grounded in verifiable, evidence-based sources.
  arXiv  Detail & Related papers  (2025-09-17T10:31:09Z)
• Combining Evidence and Reasoning for Biomedical Fact-Checking [11.555285143713315]
  CER (Combin- ing Evidence and Reasoning) is a novel framework for biomedical fact-checking.<n>It integrates scientific evidence retrieval, reasoning via large language models, and supervised veracity prediction.
  arXiv  Detail & Related papers  (2025-09-17T10:14:56Z)
• 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)
• Retrieve to Explain: Evidence-driven Predictions for Explainable Drug Target Identification [0.791663505497707]
  Retrieve to Explain (R2E) is a retrieval-based model that scores and ranks all possible answers to a research question.<n>R2E represents each answer only in terms of its supporting evidence, with the answer itself masked.<n>We developed R2E for the challenging scientific discovery task of drug target identification.
  arXiv  Detail & Related papers  (2024-02-06T15:13:17Z)
• EBOCA: Evidences for BiOmedical Concepts Association Ontology [55.41644538483948]
  This paper proposes EBOCA, an ontology that describes (i) biomedical domain concepts and associations between them, and (ii) evidences supporting these associations. Test data coming from a subset of DISNET and automatic association extractions from texts has been transformed to create a Knowledge Graph that can be used in real scenarios.
  arXiv  Detail & Related papers  (2022-08-01T18:47:03Z)

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.