4 papers
When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification
Pritam Deka, Prabhjot Singh
Biomedical fact-checking systems must do more than predict whether a claim is supported, contradicted, or unaddressed: they should also produce evidence that is faithful, complete,…
Same Facts, Different Diagnosis: Measuring and Mitigating Narrative Anchoring in Clinical Language Models
Prabhjot Singh, Pritam Deka, Vijay Chennareddy
Large language models used for clinical diagnostic reasoning are sensitive to sociolinguistic register, not just clinical content. We term this failure mode Narrative Anchoring: id…
Flowchart2Mermaid: A Vision-Language Model Powered System for Converting Flowcharts into Editable Diagram Code
Pritam Deka, Barry Devereux
Flowcharts are common tools for communicating processes but are often shared as static images that cannot be easily edited or reused. We present Flowchart2Mermaid, a lightweight we…
Structured Extraction from Business Process Diagrams Using Vision-Language Models
Pritam Deka, Barry Devereux
Business Process Model and Notation (BPMN) is a widely adopted standard for representing complex business workflows. While BPMN diagrams are often exchanged as visual images, exist…