3 papers
cs.AI2026
Behavioural Analysis of Alignment Faking
Nathaniel Mitrani Hadida, Rhea Karty, David Williams-King +1
Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deployment preferences. Understandi…
cs.AI2026
Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks
Nathaniel Mitrani Hadida, Sassan Bhanji, Cameron Tice +1
Chain-of-thought (CoT) reasoning provides a significant performance uplift to LLMs by enabling planning, exploration, and deliberation of their actions. CoT is also a powerful tool…
cs.CL2026
M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models
Aleix Torres-Camps, Nathaniel Mitrani Hadida, VÃctor Conchello Vendrell +3
Despite state-of-the-art vision-language models (VLMs) have demonstrated strong reasoning capabilities, their performance in multilingual mathematical reasoning remains underexplor…