Srivani Talakokkul

Srivani Talakokkul

Auto-generated profile, based on publicly available information

Srivani Talakokkul

Department of Emergency Medicine, Yale School of Medicine, 464 Congress Ave, New Haven, 06519, CT, USA

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 May 2026 in Artificial Intelligence in Medicine
Verified
Journal Article
Closed access
SFSamah Jamal Fodeh
Samah Jamal Fodeh
YWYan Wang
Yan Wang
LMLinhai Ma
Linhai Ma
STSrivani Talakokkul
Srivani Talakokkul
JAJordan Alpert
Jordan Alpert
SSSarah Schellhorn
Sarah Schellhorn

25 September 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
SJSamah Jarad-Fodeh
Samah Jarad-Fodeh
SSSarah Schellhorn
Sarah Schellhorn
GPGanesh Puthiaraju
Ganesh Puthiaraju
SRSreeraj Ramachandran
Sreeraj Ramachandran
EIElyas Irankhah
Elyas Irankhah
AKAfshan Khan
Afshan Khan
Structured prediction with large language models requires more than accurate labels: outputs must satisfy ontology constraints, preserve valid structure, and ensure evidence-grounded decisions under label imbalance and heterogeneous group difficulty. To resolve these challenges, we present a unified framework for robust ontology-constrained generation. First, we introduce a modular prompt-engineering architecture combining XML-style structure, expert disambiguation rules, chain-of-thought reasoning, metadata-aware decision logic, schema contracts, and a self-validation gate. This targets recurrent in-context structured generation failures, including format drift, label ambiguity, evidence hallucination, and metadata-conditioned confusion. Second, we propose STaR-DRO, which combines Tsallis mirror ascent with sparse entmax-style primal mapback, EMA-smoothed group-loss tracking, rescaled ascent signals, and bounded excess-only multipliers. This upweights only persistently hard groups without suppressing easier ones, addressing conventional DRO’s dense Shannon-entropy exponentiated-gradient updates, high-variance stochastic reweighting, positive adversarial mass on groups that are not persistently hard, and performance costs from simplex competition. We evaluate the framework on EPPC Miner, a carefully chosen, clinically grounded representation of high-stakes structured prediction requiring hierarchical label prediction and evidence-span extraction from patient-provider secure messages. Across Llama models spanning 1B to 70B parameters, our prompt engineering improves zero-shot extraction, with an average label F1 gain of +14.46 and a +17.40 Span F1 gain. Building on supervised fine-tuning, STaR-DRO further improves accuracy and robustness, increasing average label F1 by +1.08/+2.20 and reducing average group-wise validation cross-entropy by 21.3%/14.8% relative to SFT and standard DRO, respectively. These findings significantly advance the reliability of automated communication mining for patient-centered clinical care analysis.