2 papers
cs.AI2026
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu +1
Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrail…
cs.CL2025
Evaluating LLMs' Reasoning Over Ordered Procedural Steps
Adrita Anika, Md Messal Monem Miah
Reasoning over procedural sequences, where the order of steps directly impacts outcomes, is a critical capability for large language models (LLMs). In this work, we study the task…