SurgVLA-Bench supplies a hierarchical task taxonomy and multi-dimensional evaluation framework for VLA models in laparoscopic robotics simulation, showing autoregressive models excel at semantics while flow-matching models achieve higher precision but all fall short due to endoscopic view constraint
hub
Available: https://arxiv.org/abs/2503.05777
22 Pith papers cite this work, alongside 25 external citations. Polarity classification is still indexing.
22
Pith papers citing it
25
external citations · external index
hub tools
citation-role summary
background 2
citation-polarity summary
years
2026 22roles
background 2polarities
background 2representative citing papers
Med-StepBench is the first large-scale step-wise hallucination benchmark for 3D oncological PET/CT that decomposes clinical reasoning into four stages and reveals systematic VLM failures hidden by aggregate metrics.
Personalized LLM-generated plain language summaries improve lay readers' comprehension and quality ratings but increase risks of reinforcing biases and introducing hallucinations compared to static expert summaries.
Clinical narrative format beats raw JSON for LLMs up to 8B parameters on medication reconciliation but raw JSON wins at 70B scale, with omissions as the main error type.
Training-free multimodal attribution from calibrated retrieval-head attention on long documents, with a new MultAttrEval benchmark and large latency gains over prompting.
A dual clinical-computational taxonomy for medical LLM reasoning plus a five-level 5k-sample benchmark showing specialists excel at diagnosis and general models at decision support/dialogue.
Strong medical-model task scores do not guarantee process stability: omission, contradiction, and delay mainly break contradiction detection, diagnosis updating, and hallucination self-correction while final evidence grounding can look fine.
BALTO projects claim-level verification into balanced token-level rewards for RL-based hallucination mitigation in LLMs.
LLMs induce pharmacological meaning primarily from affix cues in drug names, as revealed by a framework applied to 653 drugs and localized via activation patching to early-mid layers.
Scoping review of 134 studies on LLM-as-a-Judge in healthcare finds concentration in clinical decision support and NLP, frequent use of OpenAI models with prompt engineering, and moderate-to-strong human alignment where validated.
Evaluation of 6233 MedGPTs finds 25-30% with low factual accuracy, 33.6-54.3% violating operational thresholds, and 57% of action-enabled models lacking privacy disclosures.
BELIEF improves closed-set biomedical QA by converting documents to structured evidence objects and fusing D-S symbolic belief estimation with LLM inference through reliability-aware arbitration.
Benchmark construction artifacts in hallucination detection corpora allow naive text-similarity baselines to achieve near-perfect scores, and controlled evaluations show most methods perform near chance except SAPLMA and the new DRIFT probe.
The authors built and expert-evaluated an agentic AI system integrating DEA regulatory data with dynamic scientific literature via RAG to provide accurate, context-sensitive substance use education, with mean Likert ratings of 4.18-4.35 and substantial rater agreement.
Dialectic-Med uses proponent-opponent-mediator agents with visual falsification to enforce grounded diagnostic reasoning in MLLMs, achieving SOTA accuracy and reduced hallucinations on MIMIC-CXR-VQA, VQA-RAD, and PathVQA.
A multi-stage framework with prompt calibration, rule-based filtering, semantic checks, judge LLM review, and predictive validation enables trustworthy LLM extraction of substance use disorder diagnoses from nearly 920,000 clinical notes, achieving F1 of 0.80 and superior care-engagement prediction.
Med-HEAL builds a hallucination dataset from BioMistral answers on EHRNoteQA via GPT-4o and human review, then shows self-critique improves accuracy in three of five tested LLMs without retraining.
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
CARE-ECG unifies ECG representation learning, causal graph-based diagnosis, and counterfactual assessment in an agentic LLM pipeline to improve accuracy and explanation faithfulness.
Tag-based few-shot selection yields higher precision and stability than random or similarity-based methods when using LLMs to analyze medical incidents.
Combining English and target-language web retrieval boosts medical QA for low-resource languages to match high-resource performance, while English web data benefits high-resource languages most and specialized sources like PubMed lack multilingual coverage.
The paper describes Baichuan-M4, a coordinated medical agent system that reports leading scores across static knowledge, dynamic consultation, long-context memory, retrieval, OCR, and multimodal tasks with a 3.3% hallucination rate.
citing papers explorer
-
SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for Laparoscopic Surgical Robotics
SurgVLA-Bench supplies a hierarchical task taxonomy and multi-dimensional evaluation framework for VLA models in laparoscopic robotics simulation, showing autoregressive models excel at semantics while flow-matching models achieve higher precision but all fall short due to endoscopic view constraint
-
Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models
Med-StepBench is the first large-scale step-wise hallucination benchmark for 3D oncological PET/CT that decomposes clinical reasoning into four stages and reveals systematic VLM failures hidden by aggregate metrics.
-
ReLay: Personalized LLM-Generated Plain-Language Summaries for Better Understanding, but at What Cost?
Personalized LLM-generated plain language summaries improve lay readers' comprehension and quality ratings but increase risks of reinforcing biases and introducing hallucinations compared to static expert summaries.
-
Serialisation Strategy Matters: How FHIR Data Format Affects LLM Medication Reconciliation
Clinical narrative format beats raw JSON for LLMs up to 8B parameters on medication reconciliation but raw JSON wins at 70B scale, with omissions as the main error type.
-
MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering
Training-free multimodal attribution from calibrated retrieval-head attention on long documents, with a new MultAttrEval benchmark and large latency gains over prompting.
-
Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning
A dual clinical-computational taxonomy for medical LLM reasoning plus a five-level 5k-sample benchmark showing specialists excel at diagnosis and general models at decision support/dialogue.
-
MedBench v5: A Dynamic, Process-Oriented, and Hallucination-Aware Benchmark for Clinical Multimodal Models
Strong medical-model task scores do not guarantee process stability: omission, contradiction, and delay mainly break contradiction detection, diagnosis updating, and hallucination self-correction while final evidence grounding can look fine.
-
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
BALTO projects claim-level verification into balanced token-level rewards for RL-based hallucination mitigation in LLMs.
-
What's in a Name? Morphological Shortcuts by LLMs in Pharmacology
LLMs induce pharmacological meaning primarily from affix cues in drug names, as revealed by a framework applied to 653 drugs and localized via activation patching to early-mid layers.
-
LLM-as-a-Judge in Healthcare: A Scoping Analysis of Applications, Methods, and Human Alignment
Scoping review of 134 studies on LLM-as-a-Judge in healthcare finds concentration in clinical decision support and NLP, frequent use of OpenAI models with prompt engineering, and moderate-to-strong human alignment where validated.
-
Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models
Evaluation of 6233 MedGPTs finds 25-30% with low factual accuracy, 33.6-54.3% violating operational thresholds, and 57% of action-enabled models lacking privacy disclosures.
-
BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering
BELIEF improves closed-set biomedical QA by converting documents to structured evidence objects and fusing D-S symbolic belief estimation with LLM inference through reliability-aware arbitration.
-
PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts
Benchmark construction artifacts in hallucination detection corpora allow naive text-similarity baselines to achieve near-perfect scores, and controlled evaluations show most methods perform near chance except SAPLMA and the new DRIFT probe.
-
Agentic AI for Substance Use Education: Integrating Regulatory and Scientific Knowledge Sources
The authors built and expert-evaluated an agentic AI system integrating DEA regulatory data with dynamic scientific literature via RAG to provide accurate, context-sensitive substance use education, with mean Likert ratings of 4.18-4.35 and substantial rater agreement.
-
Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent Debate
Dialectic-Med uses proponent-opponent-mediator agents with visual falsification to enforce grounded diagnostic reasoning in MLLMs, achieving SOTA accuracy and reduced hallucinations on MIMIC-CXR-VQA, VQA-RAD, and PathVQA.
-
A Multi-Stage Validation Framework for Trustworthy Large-scale Clinical Information Extraction using Large Language Models
A multi-stage framework with prompt calibration, rule-based filtering, semantic checks, judge LLM review, and predictive validation enables trustworthy LLM extraction of substance use disorder diagnoses from nearly 920,000 clinical notes, achieving F1 of 0.80 and superior care-engagement prediction.
-
Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
Med-HEAL builds a hallucination dataset from BioMistral answers on EHRNoteQA via GPT-4o and human review, then shows self-critique improves accuracy in three of five tested LLMs without retraining.
-
Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
-
CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
CARE-ECG unifies ECG representation learning, causal graph-based diagnosis, and counterfactual assessment in an agentic LLM pipeline to improve accuracy and explanation faithfulness.
-
Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
Tag-based few-shot selection yields higher precision and stability than random or similarity-based methods when using LLMs to analyze medical incidents.
-
Effects of Cross-lingual Evidence in Multilingual Medical Question Answering
Combining English and target-language web retrieval boosts medical QA for low-resource languages to match high-resource performance, while English web data benefits high-resource languages most and specialized sources like PubMed lack multilingual coverage.
-
Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care
The paper describes Baichuan-M4, a coordinated medical agent system that reports leading scores across static knowledge, dynamic consultation, long-context memory, retrieval, OCR, and multimodal tasks with a 3.3% hallucination rate.