Papers by Justin Xu
RadEval: A framework for radiology text evaluation (2025.emnlp-demos)
Copied to clipboard
Justin Xu, Xi Zhang, Javid Abderezaei, Julie Bauml, Roger Boodoo, Fatemeh Haghighi, Ali Ganjizadeh, Eric Brattain, Dave Van Veen, Zaiqiao Meng, David W Eyre, Jean-Benoit Delbrouck
| Challenge: | Evaluating automated radiology report generation systems remains a fundamental challenge in the development of safe, accurate, and clinically useful medical AI. |
| Approach: | They propose a unified, open-source framework for evaluating radiology texts that consolidates a diverse range of metrics from classic ngram overlap (BLEU) and contextual measures (BERTScore) to clinical concept-based scores (GREEN). |
| Outcome: | The framework consolidates a diverse range of metrics from ngram overlap (BLEU) and contextual measures (BERTScore) to clinical concept-based scores (F1CheXbert, F1RadGraph, RaTEScore, SRR-BERT, TemporalEntityF1) and advanced LLMbased evaluators (GREEN). |
GREEN: Generative Radiology Report Evaluation and Error Notation (2024.findings-emnlp)
Copied to clipboard
Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Md, Michael Moseley, Curtis Langlotz, Akshay Chaudhari, Jean-Benoit Delbrouck
| Challenge: | Existing automated evaluation metrics fail to consider factual correctness or are limited in their interpretability. |
| Approach: | They propose a radiology report evaluation metric that leverages natural language understanding of language models to identify and explain clinically significant errors. |
| Outcome: | The proposed method demonstrates higher correlation with expert error counts and higher alignment with expert preferences when compared to previous methods. |
Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors (2023.acl-long)
Copied to clipboard
Liyan Tang, Tanya Goyal, Alex Fabbri, Philippe Laban, Jiacheng Xu, Semih Yavuz, Wojciech Kryscinski, Justin Rousseau, Greg Durrett
| Challenge: | Abstractive summarization systems still include factual errors in generated summaries despite recent improvements in factuality detection . |
| Approach: | They aggregate factuality error annotations from nine existing datasets and stratify them according to the underlying summarization model. |
| Outcome: | The proposed method improves on the ChatGPT-based model and shows that it is not superior for all error types. |
Morphological Segmentation for Low Resource Languages (2020.lrec-1)
Copied to clipboard
Justin Mott, Ann Bies, Stephanie Strassel, Jordan Kodner, Caitlin Richter, Hongzhi Xu, Mitchell Marcus
| Challenge: | a new corpus of annotated morphological data is described for the DARPA LORELEI Program . the data is annotating 9 low resource languages and root information for 7 of the languages . |
| Approach: | This paper describes a new morphology resource created by Linguistic Data Consortium and the University of Pennsylvania for the DARPA LORELEI Program. |
| Outcome: | The annotated corpus provides a gold standard for unsupervised morphological segmenters and analyzers . the language-specific annotation guidelines were language-independent, but included morphology paradigms and other specifications. |
Automated Structured Radiology Report Generation (2025.acl-long)
Copied to clipboard
Jean-Benoit Delbrouck, Justin Xu, Johannes Moll, Alois Thomas, Zhihong Chen, Sophie Ostmeier, Asfandyar Azhar, Kelvin Zhenghao Li, Andrew Johnston, Christian Bluethgen, Eduardo Pontes Reis, Mohamed S Muneer, Maya Varma, Curtis Langlotz
| Challenge: | Existing models struggle to produce consistent, clinically meaningful reports and standard evaluation metrics fail to capture the nuances of radiological interpretation. |
| Approach: | They propose to reformulate free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. |
| Outcome: | The proposed task reformulates free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. |
CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback (2025.acl-long)
Copied to clipboard
Dennis Hein, Zhihong Chen, Sophie Ostmeier, Justin Xu, Maya Varma, Eduardo Pontes Reis, Arne Edward Michalson Md, Christian Bluethgen, Hyun Joo Shin, Curtis Langlotz, Akshay S Chaudhari
| Challenge: | Radiologists are a crucial role in translating medical images into actionable reports . however, the field faces staffing shortages and increasing workloads . |
| Approach: | They propose an automated pipeline for preference feedback focusing on chest X-ray radiology report generation (RRG) method leverages publicly available datasets containing pairs of images and radiologist-written reference reports with reference-based metrics, or Judges. |
| Outcome: | The proposed pipeline achieves state-of-the-art CheXbert scores on the MIMIC-CXR dataset while on average maintaining robust performance across six additional image perception and reasoning tasks. |
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization (2026.findings-acl)
Copied to clipboard
Yuanchen Wu, Saurabh Verma, Justin Lee, Fangzhou Xiong, Poppy Zhang, Amel Awadelkarim, Xu Chen, Yubai Yuan, Shawndra Hill
| Challenge: | Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization methods assume access to ground-truth references that are costly to obtain. |
| Approach: | They propose a sample-efficient framework for label-free prompt optimization based on pairwise preference feedback from an LLM judge. |
| Outcome: | Experiments on BIG-bench Hard and MS MARCO show that the proposed framework identifies stronger prompts than label-free baselines while offering favorable quality–cost trade-offs. |
Tree-of-Quote Prompting Improves Factuality and Attribution in Multi-Hop and Medical Reasoning (2025.emnlp-main)
Copied to clipboard
Justin Xu, Yiming Li, Zizheng Zhang, Augustine Yui Hei Luk, Mayank Jobanputra, Samarth Oza, Ashley Murray, Meghana Reddy Kasula, Andrew Parker, David W Eyre
| Challenge: | Large language models (LLMs) produce fluent but factually incorrect outputs, a phenomenon commonly referred to as hallucination. |
| Approach: | They propose a Tree-of-Quote framework that decomposes complex questions into subquestions and generates quotes to support each step without retrieval. |
| Outcome: | Experiments on StrategyQA, 2WikiMultiHopQA, MuSiQue, MoreHopQ, and MedQA show that ToQ improves factuality and attribution over baselines. |
Instructional Agents: Reducing Teaching Faculty Workload through Multi-Agent Instructional Design (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing AI-assisted educational tools focus on isolated tasks, but lack end-to-end workflows for instructional design. |
| Approach: | They propose a multi-agent large language model framework to automate end-to-end course material generation. |
| Outcome: | The proposed framework reduces development time and human workload while reducing human involvement. |