ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction

• URL: http://arxiv.org/abs/2608.03154v1
• Date: Tue, 04 Aug 2026 05:36:19 GMT
• Title: ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation Extraction
• Abstract summary: ANCHOR-RE is a framework that integrates ontology-guided reasoning, external knowledge grounding, and data-driven verification rules.<n>We evaluated it on three BioRE benchmarks (SemRepGS, DDI, and ChemProt) using both proprietary and open-weight LLMs.<n>Neuro-symbolic reasoning can improve the reliability of LLM-based BioRE without fine-tuning.
• Score: 5.624249017853434
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Biomedical relation extraction (BioRE) extracts structured knowledge from biomedical literature for applications such as knowledge base construction and hypothesis generation. Traditional symbolic systems such as SemRep provide high precision but limited recall, while large language models (LLMs) offer stronger contextual reasoning but remain prone to false-positive predictions. We developed ANCHOR-RE, a framework that integrates ontology-guided reasoning, external knowledge grounding, and data-driven verification rules into LLM inference. We evaluated it on three BioRE benchmarks (SemRepGS, DDI, and ChemProt) using both proprietary and open-weight LLMs. To assess generalizability beyond benchmark datasets while reducing potential evaluation bias from LLM pretraining contamination, we conducted a temporal evaluation using 100 biomedical articles published in 2026. With the proprietary backbone, ANCHOR-RE outperformed direct LLM prompting, improving micro-F1 from 0.654 to 0.676 on SemRepGS, from 0.769 to 0.872 on DDI, and from 0.939 to 0.941 on ChemProt. On DDI and ChemProt, it also outperformed previously reported inference-only methods and approached fine-tuned or instruction-tuned systems without parameter updates. Similar performance gains observed with open-weight LLMs indicate that the benefits were not limited to the proprietary backbone. On the post-cutoff set, manual assessment of 500 randomly sampled predictions yielded a precision of 69%, maintaining consistent precision on previously unseen biomedical literature. Neuro-symbolic reasoning can improve the reliability of LLM-based BioRE without fine-tuning. Results across multiple benchmarks, model families, and post-cutoff literature support ANCHOR-RE as a practical training-free approach to biomedical literature mining.

Related papers

• Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback [56.69850045068714]
  We introduce textitInfluence-Guided Regression (IGSR), a method that frames equation discovery as an iterative two-step process.<n>We demonstrate IGSRs effectiveness on a diverse suite of benchmarks, including LLM-SRBench, pharmacological PKPD models, an epidemiological simulation, and real-world genomic data.
  arXiv  Detail & Related papers  (2026-05-27T23:48:01Z)
• SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation [42.644852156101685]
  Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread.<n>We propose textbfSL-BiLEM (Structured Learnable Behavior-in-the-Loop Epidemic Model), leveraging physical constraints as regularization for robust extrapolation.
  arXiv  Detail & Related papers  (2026-05-26T08:46:04Z)
• MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies [0.8322112116381115]
  Large language models (LLMs) have saturated standard medical benchmarks that test factual recall.<n>We introduce MedMeta, the first benchmark designed to evaluate an LLM's ability to generate conclusions from medical meta-analyses.
  arXiv  Detail & Related papers  (2026-05-10T17:20:39Z)
• Multi-Task LLM with LoRA Fine-Tuning for Automated Cancer Staging and Biomarker Extraction [6.53191669778827]
  This study introduces a parameter-efficient, multi-task framework for automating the extraction of Tumor-Node-Metastasis (TNM) staging, histologic grade, and biomarkers.<n>We fine-tune a Llama-3-8B-Instruct encoder using Low-Rank Adaptation (LoRA) on a curated, expert-verified dataset of 10,677 reports.
  arXiv  Detail & Related papers  (2026-04-14T22:26:30Z)
• Eligibility-Aware Evidence Synthesis: An Agentic Framework for Clinical Trial Meta-Analysis [49.83108591873481]
  EligMeta is an agentic framework that integrates automated trial discovery with eligibility-aware meta-analysis.<n>The framework structures eligibility criteria and computes similarity-based study weights reflecting population alignment between target trials.
  arXiv  Detail & Related papers  (2026-04-03T03:18:50Z)
• PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation [51.96735866702332]
  PREBA is a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging aggregation.<n> PREBA significantly improves performance-for instance, reducing MAE by up to 40% and raising R2 from -0.13 to 0.62 over zero-shot inference.
  arXiv  Detail & Related papers  (2026-02-27T07:19:23Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• RELATE: Relation Extraction in Biomedical Abstracts with LLMs and Ontology Constraints [2.844531679990474]
  We introduce RELATE, a three-stage pipeline that maps LLM-extracted relations to standardized KGs.<n>The pipeline includes: (1) preprocessing with embeddings, (2) similarity-based retrieval enhanced with SapBERT, and (3)-based reranking with explicit negation handling.<n>On the ChemProt benchmark, RELATE achieves 52% exact match and 94% accuracy@10, in 2,400 HEAL Project abstracts.
  arXiv  Detail & Related papers  (2025-09-23T14:21:46Z)
• From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations [45.414878840652115]
  Large language models (LLMs) have demonstrated promising performance on medical benchmarks.<n>However, their ability to perform medical calculations remains underexplored and poorly evaluated.<n>In this work, we revisit medical calculation evaluation with a stronger focus on clinical trustworthiness.
  arXiv  Detail & Related papers  (2025-09-20T09:10:26Z)
• DrugReasoner: Interpretable Drug Approval Prediction with a Reasoning-augmented Language Model [0.0]
  We present DrugReasoner, a reasoning-based large language model (LLM) built on the LLaMA architecture.<n>DrugReasoner integrates molecular descriptors with comparative reasoning against structurally similar approved and unapproved compounds.<n>It achieved robust performance with an AUC of 0.732 and an F1 score of 0.729 on the validation set and 0.725 and 0.718 on the test set.
  arXiv  Detail & Related papers  (2025-08-26T01:14:14Z)
• LLM Agent Swarm for Hypothesis-Driven Drug Discovery [2.7036595757881323]
  PharmaSwarm is a unified multi-agent framework that orchestrates specialized "agents" to propose, validate, and refine hypotheses for novel drug targets and lead compounds.<n>By acting as an AI copilot, PharmaSwarm can accelerate translational research and deliver high-confidence hypotheses more efficiently than traditional pipelines.
  arXiv  Detail & Related papers  (2025-04-24T22:27:50Z)
• Quantifying the Reasoning Abilities of LLMs on Real-world Clinical Cases [48.87360916431396]
  We introduce MedR-Bench, a benchmarking dataset of 1,453 structured patient cases, annotated with reasoning references.<n>We propose a framework encompassing three critical examination recommendation, diagnostic decision-making, and treatment planning, simulating the entire patient care journey.<n>Using this benchmark, we evaluate five state-of-the-art reasoning LLMs, including DeepSeek-R1, OpenAI-o3-mini, and Gemini-2.0-Flash Thinking, etc.
  arXiv  Detail & Related papers  (2025-03-06T18:35:39Z)
• Comparing Hyper-optimized Machine Learning Models for Predicting Efficiency Degradation in Organic Solar Cells [38.647921189039934]
  This work presents a set of optimal machine learning (ML) models to represent the temporal degradation suffered by the power conversion efficiency (PCE) of organic solar cells (OSCs)<n>We generated a database with 996 entries, which includes up to 7 variables regarding both the manufacturing process and environmental conditions for more than 180 days.<n>The accuracy achieved reaches values of the coefficient determination (R2) widely exceeding 0.90, whereas the root mean squared error (RMSE), sum of squared error (SSE), and mean absolute error (MAE)>1% of the target value, the PCE.
  arXiv  Detail & Related papers  (2024-03-29T22:05:26Z)
• Unassisted Noise Reduction of Chemical Reaction Data Sets [59.127921057012564]
  We propose a machine learning-based, unassisted approach to remove chemically wrong entries from data sets. Our results show an improved prediction quality for models trained on the cleaned and balanced data sets.
  arXiv  Detail & Related papers  (2021-02-02T09:34:34Z)

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.