3 papers
cs.AI2026
Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure
Caglar Yildirim
Large language models (LLMs) are increasingly deployed as tool-using agents, shifting safety concerns from harmful text generation to harmful task completion. Deployed systems ofte…
cs.LG2026
The Impact of Post-training on Data Contamination
Muhammed Yusuf Kocyigit, Caglar Yildirim
We present a controlled study of how dataset contamination interacts with the post-training stages now standard in large language model training pipelines. Starting from clean chec…
cs.HC2025
Conversational AI as a Coding Assistant: Understanding Programmers' Interactions with and Expectations from Large Language Models for Coding
Mehmet Akhoroz, Caglar Yildirim
Conversational AI interfaces powered by large language models (LLMs) are increasingly used as coding assistants. However, questions remain about how programmers interact with LLM-b…