collaborators

6 papers

cs.AI2025

Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering

Josefa Lia Stoisser, Lawrence Phillips, Aditya Misra +5

Synthetic chain-of-thought (CoT) traces are widely used to train large reasoning models (LRMs), improving generalization by providing step-level supervision. Yet most approaches re…

cs.DB2025

Query, Don't Train: Privacy-Preserving Tabular Prediction from EHR Data via SQL Queries

Josefa Lia Stoisser, Marc Boubnovski Martell, Kaspar Märtens +4

Electronic health records (EHRs) contain richly structured, longitudinal data essential for predictive modeling, yet stringent privacy regulations (e.g., HIPAA, GDPR) often restric…

cs.AI2025

Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoning

Josefa Lia Stoisser, Marc Boubnovski Martell, Lawrence Phillips +6

Large language model (LLM) agents are increasingly deployed in structured biomedical data environments, yet they often produce fluent but overconfident outputs when reasoning over…

q-bio.GN2025

Modeling Gene Expression Distributional Shifts for Unseen Genetic Perturbations

Kalyan Ramakrishnan, Jonathan G. Hedley, Sisi Qu +5

We train a neural network to predict distributional responses in gene expression following genetic perturbations. This is an essential task in early-stage drug discovery, where suc…

cs.CL2025

STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing

Josefa Lia Stoisser, Marc Boubnovski Martell, Lawrence Phillips +2

We propose STRuCT-LLM, a unified framework for training large language models (LLMs) to perform structured reasoning over both relational and graph-structured data. Our approach jo…

cs.CL2025

Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning

Josefa Lia Stoisser, Marc Boubnovski Martell, Julien Fauqueur

This work reframes the Text-to-SQL task as a pathway for teaching large language models (LLMs) to reason over and manipulate tabular data--moving beyond the traditional focus on qu…