Steven Bedrick

Deepak Gupta, Dina Demner-Fushman, William Hersh et al.

Recent advances in large language models (LLMs) have made significant progress across multiple biomedical tasks, including biomedical question answering, lay-language summarization of the biomedical literature, and clinical note summarization. These models have demonstrated strong capabilities in processing and synthesizing complex biomedical information and in generating fluent, human-like responses. Despite these advancements, hallucinations or confabulations remain key challenges when using LLMs in biomedical and other high-stakes domains. Inaccuracies may be particularly harmful in high-risk situations, such as medical question answering, making clinical decisions, or appraising biomedical research. Studies on the evaluation of the LLMs' abilities to ground generated statements in verifiable sources have shown that models perform significantly

Kurt Miller, Qiuhao Lu, William Hersh et al.

Clinical document metadata, such as document type, structure, author role, medical specialty, and encounter setting, is essential for accurate interpretation of information captured in clinical documents. However, vast documentation heterogeneity and drift over time challenge harmonization of document metadata. Automated extraction methods have emerged to coalesce metadata from disparate practices into target schema. This scoping review aims to catalog research on clinical document metadata extraction, identify methodological trends and applications, and highlight gaps. We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines to identify articles that perform clinical document metadata extraction. We initially found and screened 266 articles published between January 2011 and August 2025, then comprehensively reviewed 67 we deemed relevant to our study. Among the articles included, 45 were methodological, 17 used document metadata as features in a downstream application, and 5 analyzed document metadata composition. We observe myriad purposes for methodological study and application types. Available labelled public data remains sparse except for structural section datasets. Methods for extracting document metadata have progressed from largely rule-based and traditional machine learning with ample feature engineering to transformer-based architectures with minimal feature engineering. The emergence of large language models has enabled broader exploration of generalizability across tasks and datasets, allowing the possibility of advanced clinical text processing systems. We anticipate that research will continue to expand into richer document metadata representations and integrate further into clinical applications and workflows.

Steven Bedrick, A. Seza Doğruöz, Sergiu Nisioi

Synthetic data sets are used across linguistic domains and NLP tasks, particularly in scenarios where authentic data is limited (or even non-existent). One such domain is that of clinical (healthcare) contexts, where there exist significant and long-standing challenges (e.g., privacy, anonymization, and data governance) which have led to the development of an increasing number of synthetic datasets. One increasingly important category of clinical dataset is that of clinical dialogues which are especially sensitive and difficult to collect, and as such are commonly synthesized. While such synthetic datasets have been shown to be sufficient in some situations, little theory exists to inform how they may be best used and generalized to new applications. In this paper, we provide an overview of how synthetic datasets are created, evaluated and being used for dialogue related tasks in the medical domain. Additionally, we propose a novel typology for use in classifying types and degrees of data synthesis, to facilitate comparison and evaluation.

Shiran Dudy, Steven Bedrick, Bonnie Webber

Many NLG tasks such as summarization, dialogue response, or open domain question answering focus primarily on a source text in order to generate a target response. This standard approach falls short, however, when a user's intent or context of work is not easily recoverable based solely on that source text -- a scenario that we argue is more of the rule than the exception. In this work, we argue that NLG systems in general should place a much higher level of emphasis on making use of additional context, and suggest that relevance (as used in Information Retrieval) be thought of as a crucial tool for designing user-oriented text-generating tasks. We further discuss possible harms and hazards around such personalization, and argue that value-sensitive design represents a crucial path forward through these challenges.

Kirk Roberts, Tasmeer Alam, Steven Bedrick et al.

We present an overview of the TREC-COVID Challenge, an information retrieval (IR) shared task to evaluate search on scientific literature related to COVID-19. The goals of TREC-COVID include the construction of a pandemic search test collection and the evaluation of IR methods for COVID-19. The challenge was conducted over five rounds from April to July, 2020, with participation from 92 unique teams and 556 individual submissions. A total of 50 topics (sets of related queries) were used in the evaluation, starting at 30 topics for Round 1 and adding 5 new topics per round to target emerging topics at that state of the still-emerging pandemic. This paper provides a comprehensive overview of the structure and results of TREC-COVID. Specifically, the paper provides details on the background, task structure, topic structure, corpus, participation, pooling, assessment, judgments, results, top-performing systems, lessons learned, and benchmark datasets.

Shiran Dudy, Steven Bedrick

Current evaluation metrics for language modeling and generation rely heavily on the accuracy of predicted (or generated) words as compared to a reference ground truth. While important, token-level accuracy only captures one aspect of a language model's behavior, and ignores linguistic properties of words that may allow some mis-predicted tokens to be useful in practice. Furthermore, statistics directly tied to prediction accuracy (including perplexity) may be confounded by the Zipfian nature of written language, as the majority of the prediction attempts will occur with frequently-occurring types. A model's performance may vary greatly between high- and low-frequency words, which in practice could lead to failure modes such as repetitive and dull generated text being produced by a downstream consumer of a language model. To address this, we propose two new intrinsic evaluation measures within the framework of a simple word prediction task that are designed to give a more holistic picture of a language model's performance. We evaluate several commonly-used large English language models using our proposed metrics, and demonstrate that our approach reveals functional differences in performance between the models that are obscured by more traditional metrics.

Ellen Voorhees, Tasmeer Alam, Steven Bedrick et al.

TREC-COVID is a community evaluation designed to build a test collection that captures the information needs of biomedical researchers using the scientific literature during a pandemic. One of the key characteristics of pandemic search is the accelerated rate of change: the topics of interest evolve as the pandemic progresses and the scientific literature in the area explodes. The COVID-19 pandemic provides an opportunity to capture this progression as it happens. TREC-COVID, in creating a test collection around COVID-19 literature, is building infrastructure to support new research and technologies in pandemic search.

Sijia Liu, Yanshan Wang, Andrew Wen et al.

Background: Widespread adoption of electronic health records (EHRs) has enabled secondary use of EHR data for clinical research and healthcare delivery. Natural language processing (NLP) techniques have shown promise in their capability to extract the embedded information in unstructured clinical data, and information retrieval (IR) techniques provide flexible and scalable solutions that can augment the NLP systems for retrieving and ranking relevant records. Methods: In this paper, we present the implementation of Cohort Retrieval Enhanced by Analysis of Text from EHRs (CREATE), a cohort retrieval system that can execute textual cohort selection queries on both structured and unstructured EHR data. CREATE is a proof-of-concept system that leverages a combination of structured queries and IR techniques on NLP results to improve cohort retrieval performance while adopting the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) to enhance model portability. The NLP component empowered by cTAKES is used to extract CDM concepts from textual queries. We design a hierarchical index in Elasticsearch to support CDM concept search utilizing IR techniques and frameworks. Results: Our case study on 5 cohort identification queries evaluated using the IR metric, P@5 (Precision at 5) at both the patient-level and document-level, demonstrates that CREATE achieves an average P@5 of 0.90, which outperforms systems using only structured data or only unstructured data with average P@5s of 0.54 and 0.74, respectively.