Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions

ArXi:2605.09893v1 Announce Type: cross Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy termed "value-action gap." In this work, we argue that this gap persists even under explicit reasoning, revealing a deeper failure mode we call "Pseudo-Deliberation": the appearance of principled reasoning without corresponding behavioral alignment. To study this systematically, we