Beyond Long Context: When Semantics Matter More than Tokens

• URL: http://arxiv.org/abs/2510.25816v1
• Date: Wed, 29 Oct 2025 16:41:44 GMT
• Title: Beyond Long Context: When Semantics Matter More than Tokens
• Abstract summary: Electronic Health Records store clinical documentation as base64 attachments encoded in FHIR DocumentReference resources.<n>The Clinical Entity Augmented Retrieval (CLEAR) method, introduced by Lopez et al. 2025, uses entity aware retrieval.<n>CLEAR achieved a 58.3 percent win rate, an average semantic similarity of 0.878, and used 78 percent fewer tokens than wide context processing.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Electronic Health Records (EHR) store clinical documentation as base64 encoded attachments in FHIR DocumentReference resources, which makes semantic question answering difficult. Traditional vector database methods often miss nuanced clinical relationships. The Clinical Entity Augmented Retrieval (CLEAR) method, introduced by Lopez et al. 2025, uses entity aware retrieval and achieved improved performance with an F1 score of 0.90 versus 0.86 for embedding based retrieval, while using over 70 percent fewer tokens. We developed a Clinical Notes QA Evaluation Platform to validate CLEAR against zero shot large context inference and traditional chunk based retrieval augmented generation. The platform was tested on 12 clinical notes ranging from 10,000 to 65,000 tokens representing realistic EHR content. CLEAR achieved a 58.3 percent win rate, an average semantic similarity of 0.878, and used 78 percent fewer tokens than wide context processing. The largest performance gains occurred on long notes, with a 75 percent win rate for documents exceeding 65,000 tokens. These findings confirm that entity aware retrieval improves both efficiency and accuracy in clinical natural language processing. The evaluation framework provides a reusable and transparent benchmark for assessing clinical question answering systems where semantic precision and computational efficiency are critical.

Related papers

• Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture [71.46525715889656]
  General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement.<n>We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record.<n>We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions.
  arXiv  Detail & Related papers  (2026-04-29T17:59:28Z)
• The Validity Gap in Health AI Evaluation: A Cross-Sectional Analysis of Benchmark Composition [0.19599274203282302]
  We analyzed 18,707 consumer health queries across six public benchmarks.<n>Findings: Clinical composition remains misaligned with real-world needs.<n>Field must adopt standardized query profiling to align evaluation with the full complexity of clinical practice.
  arXiv  Detail & Related papers  (2026-03-18T21:31:19Z)
• Agentic Cognitive Profiling: Realigning Automated Alzheimer's Disease Detection with Clinical Construct Validity [66.94391219005291]
  This paper proposes Agentic Cognitive Profiling (ACP), an agentic framework that realigns automated screening with clinical protocol logic.<n>Central to our design is decoupling semantic understanding from measurement by delegating all quantification to deterministic function calling.<n>ACP achieves 90.5% score match rate in task examination and 85.3% accuracy in AD prediction, surpassing popular baselines.
  arXiv  Detail & Related papers  (2026-03-18T06:15:35Z)
• LiveClin: A Live Clinical Benchmark without Leakage [50.45415584327275]
  LiveClin is a live benchmark designed for approximating real-world clinical practice.<n>We transform authentic patient cases into complex, multimodal evaluation scenarios that span the entire clinical pathway.<n>Our evaluation of 26 models on LiveClin reveals the profound difficulty of these real-world scenarios, with the top-performing model achieving a Case Accuracy of just 35.7%.
  arXiv  Detail & Related papers  (2026-02-18T03:59:46Z)
• Explainable Admission-Level Predictive Modeling for Prolonged Hospital Stay in Elderly Populations: Challenges in Low- and Middle-Income Countries [65.4286079244589]
  Prolonged length of stay (pLoS) is a significant factor associated with the risk of adverse in-hospital events.<n>We develop and explain a predictive model for pLos using admission-level patient and hospital administrative data.
  arXiv  Detail & Related papers  (2026-01-07T23:35:24Z)
• Adoption, usability and perceived clinical value of a UK AI clinical reference platform (iatroX): a mixed-methods formative evaluation of real-world usage and a 1,223-respondent user survey [0.0]
  Clinicians face growing information overload from biomedical literature and guidelines, hindering evidence-based care.<n>We describe iatroX, a UK-centred RAG-based clinical reference platform.<n>We report early adoption, usability, and perceived clinical value from a formative implementation evaluation.
  arXiv  Detail & Related papers  (2025-09-25T14:03:04Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• Detection of Adverse Drug Events in Dutch clinical free text documents using Transformer Models: benchmark study [2.6758306285161075]
  We establish a benchmark for adverse drug event (ADE) detection in Dutch clinical free-text documents.<n>We trained a Bidirectional Long Short-Term Memory (Bi-LSTM) model and four transformer-based Dutch and/or multilingual encoder models.<n>We evaluated our ADE RC models internally using the gold standard (two-step task) and predicted entities.
  arXiv  Detail & Related papers  (2025-07-25T16:02:02Z)
• LLM-based Prompt Ensemble for Reliable Medical Entity Recognition from EHRs [4.262074310505135]
  This paper explores prompt-based medical entity recognition using large language models (LLMs)<n>GPT-4o with prompt ensemble achieved the highest classification performance with an F1-score of 0.95 and recall of 0.98.<n>The ensemble method improved reliability by aggregating outputs through embedding-based similarity and majority voting.
  arXiv  Detail & Related papers  (2025-05-13T16:11:29Z)
• Development and Validation of the Provider Documentation Summarization Quality Instrument for Large Language Models [3.0569643495382173]
  The Provider Summarization Quality Instrument (PDSQI-9) was developed to evaluate LLM-generated clinical summaries.<n> validation included Pearson correlation for substantive validity, factor analysis and Cronbach's alpha for structural validity.<n>The PDSQI-9 demonstrated strong internal consistency and high inter-rater reliability.
  arXiv  Detail & Related papers  (2025-01-15T17:47:57Z)
• Leveraging deep active learning to identify low-resource mobility functioning information in public clinical notes [0.157286095422595]
  First public annotated dataset specifically on the Mobility domain of the International Classification of Functioning, Disability and Health (ICF) We utilize the National NLP Clinical Challenges (n2c2) research dataset to construct a pool of candidate sentences using keyword expansion. Our final dataset consists of 4,265 sentences with a total of 11,784 entities, including 5,511 Action entities, 5,328 Mobility entities, 306 Assistance entities, and 639 Quantification entities.
  arXiv  Detail & Related papers  (2023-11-27T15:53:11Z)
• A Federated Learning Framework for Stenosis Detection [70.27581181445329]
  This study explores the use of Federated Learning (FL) for stenosis detection in coronary angiography images (CA) Two heterogeneous datasets from two institutions were considered: dataset 1 includes 1219 images from 200 patients, which we acquired at the Ospedale Riuniti of Ancona (Italy) dataset 2 includes 7492 sequential images from 90 patients from a previous study available in the literature.
  arXiv  Detail & Related papers  (2023-10-30T11:13:40Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)
• Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts [56.72488923420374]
  Pre-trained language models (LMs) have shown great potential for cross-lingual transfer in low-resource settings. We show the few-shot cross-lingual transfer property of LMs for named recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke.
  arXiv  Detail & Related papers  (2022-04-10T21:46:52Z)
• Detecting of a Patient's Condition From Clinical Narratives Using Natural Language Representation [0.3149883354098941]
  This paper proposes a joint clinical natural language representation learning and supervised classification framework. The novel framework jointly discovers distributional syntactic and latent semantic (representation learning) from contextual clinical narrative inputs. The proposed framework yields an overall classification performance with accuracy, recall, and precision of 89 % and 88 %, 89 %, respectively.
  arXiv  Detail & Related papers  (2021-04-08T17:16:04Z)
• NUVA: A Naming Utterance Verifier for Aphasia Treatment [49.114436579008476]
  Assessment of speech performance using picture naming tasks is a key method for both diagnosis and monitoring of responses to treatment interventions by people with aphasia (PWA) Here we present NUVA, an utterance verification system incorporating a deep learning element that classifies 'correct' versus'incorrect' naming attempts from aphasic stroke patients. When tested on eight native British-English speaking PWA the system's performance accuracy ranged between 83.6% to 93.6%, with a 10-fold cross-validation mean of 89.5%.
  arXiv  Detail & Related papers  (2021-02-10T13:00:29Z)
• Collaborative residual learners for automatic icd10 prediction using prescribed medications [45.82374977939355]
  We propose a novel collaborative residual learning based model to automatically predict ICD10 codes employing only prescriptions data. We obtain multi-label classification accuracy of 0.71 and 0.57 of average precision, 0.57 and 0.38 of F1-score and 0.73 and 0.44 of accuracy in predicting principal diagnosis for inpatient and outpatient datasets respectively.
  arXiv  Detail & Related papers  (2020-12-16T07:07:27Z)

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.