6 papers
A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems
ÄorÄe Klisura, Astrid R Bernaga Torres, Anna Karen Gárate-Escamilla +4
Privacy policies inform users about data collection and usage, yet their complexity limits accessibility for diverse populations. Existing Privacy Policy Question Answering (QA) sy…
How AI Forecasts AI Jobs: Benchmarking LLM Predictions of Labor Market Changes
Sheri Osborn, Rohit Valecha, H. Raghav Rao +2
Artificial intelligence is reshaping labor markets, yet we lack tools to systematically forecast its effects on employment. This paper introduces a benchmark for evaluating how wel…
Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models
ÄorÄe Klisura, Joseph Khoury, Ashish Kundu +2
Access control is a cornerstone of secure computing, yet large language models often blur role boundaries by producing unrestricted responses. We study role-conditioned refusals, f…
Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach
James Ford, Anthony Rios
Large language models can translate natural-language chart descriptions into runnable code, yet approximately 15\% of the generated scripts still fail to execute, even after superv…
UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting
Sara Shields-Menard, Zach Reimers, Joshua Gardner +2
We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps:…
Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems
ÄorÄe Klisura, Anthony Rios
Text-to-SQL systems empower users to interact with databases using natural language, automatically translating queries into executable SQL code. However, their reliance on database…