1 citations · 1 across the 10 of their papers we have counts for
11 papers
Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments
Linhai Ma, Yan Wang, Lingfei Qian +2
Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no reference for it, that is, no text t…
Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models
Linhai Ma, Rita El Hachem, Mahatab El Hajj +2
Crisis helplines assess suicide risk through structured interviews, a process that is slow and dependent on operator training and workload. Natural language processing could suppor…
Factorized Hypothesis Search for Evidence-to-Taxonomy Retrieval
Linhai Ma, Ethan F. Wei, Xueqing Peng +3
Large-taxonomy retrieval often assumes that the input already expresses the target concept. In many settings, however, the input is indirect evidence, such as a table cell whose me…
PVminerLLM2: Improving Structured Extraction of Patient Voice via Preference Optimization
Samah Fodeh, Linhai Ma, Ganesh Puthiaraju +7
Motivation: Patient-generated text contains critical information on patients' lived experiences, social context, and care engagement, but remains largely unstructured, limiting its…
Herculean: An Agentic Benchmark for Financial Intelligence
Xueqing Peng, Zhuohan Xie, Yupeng Cao +60
As AI agents advance, the central question is no longer whether they can solve isolated financial tasks, but whether their capabilities generalize across complete professional work…
EPPC-OASIS: Ontology-Aware Adaptation and Structured Inference Refinement for Electronic Patient-Provider Communication Mining in Secure Messages
Samah Fodeh, Sreeraj Ramachandran, Elyas Irankhah +7
Secure patient-provider messages contain clinically important communication behaviors that are difficult to characterize manually at scale. The Electronic Patient-Provider Communic…
STaR-DRO: Stateful Tsallis Reweighting for Group-Robust Structured Prediction
Samah Fodeh, Ganesh Puthiaraju, Elyas Irankhah +5
Structured prediction with large language models requires outputs that are label-accurate, ontology-constrained, structurally valid, and evidence-grounded under label imbalance and…
PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models
Samah Fodeh, Linhai Ma, Ganesh Puthiaraju +5
Motivation: Patient-generated text contains critical information about patients' lived experiences, social circumstances, and engagement in care, including factors that strongly in…
TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation
Samah Fodeh, Linhai Ma, Ganesh Puthiaraju +5
Direct Preference Optimization (DPO) is effective for offline alignment but poorly matched to ontology-driven structured prediction, where preferred and rejected JSON often differ…
PVminer: A Domain-Specific Tool to Detect the Patient Voice in Patient Generated Data
Samah Fodeh, Linhai Ma, Yan Wang +6
Patient-generated text such as secure messages, surveys, and interviews contains rich expressions of the patient voice (PV), reflecting communicative behaviors and social determina…
EPPCMinerBen: A Novel Benchmark for Evaluating Large Language Models on Electronic Patient-Provider Communication via the Patient Portal
Samah Fodeh, Yan Wang, Linhai Ma +3
Effective communication in health care is critical for treatment outcomes and adherence. With patient-provider exchanges shifting to secure messaging, analyzing electronic patient-…