2 papers
cs.CL2026
Evaluation Awareness Is Not One Capability: Evidence from Open Language Models
Nilesh Nayan, Aishwarya Sampath Kumar, Rishiraj Girmal +5
Safety benchmarks assume that test-condition behavior predicts deployment behavior, an assumption that fails if models detect evaluation cues and adapt. This opens a gap between be…
cs.CL2025
Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation
Jaechul Roh, Varun Gandhi, Shivani Anilkumar +1
Large Language Models (LLMs) have achieved remarkable success in tasks requiring complex reasoning, such as code generation, mathematical problem solving, and algorithmic synthesis…