Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
When Is Benchmark Contamination Detectable? Information Limits and Power-Calibrated Audits
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
Behavioral contamination detectors can return "no evidence" either because a benchmark is clean or because the audit has little power. We formalize this distinction for a benchmark…
cs.AI2026
Causal Consistency Regularization: Training Verifiably Sensitive Reasoning in Large Language Models
Sanjeda Akter, Ibne Farabi Shihab, Anuj Sharma
Large language models can produce correct answers while relying on flawed reasoning traces, partly because common training objectives reward final-answer correctness rather than fa…