The core of knowledge distillation lies in transferring the teacher’s rich ’dark knowledge’—subtle probabilistic patterns that reveal how classes are related and the distribution of uncertainties. While this idea is well established, teachers trained with conventional cross-entropy often fail to preserve such signals. Their distributions appear decisive but are in fact brittle, offering little beyond the hard label. This overconfidence is especially problematic in high-cardinality tasks, where subtle distinctions among many plausible classes are crucial for guiding compact students. To address this limitation, we revisit distillation from a distributional perspective and propose Calibrated Uncertainty Distillation (CUD), a framework that makes dark knowledge more faithfully accessible. Instead of uncritically inheriting the teacher’s overconfidence, CUD encourages the teacher to expose informative uncertainty and guides the student to learn from calibrated targets instead of overly sharpened predictions. By shaping the teacher’s predictive distribution before transfer, our approach balances accuracy and calibration, allowing students to benefit from both confident signals on easy cases and structured uncertainty on hard ones.

Large Language Models (LLMs) often succumb to adversarial prompts, a phenomenon popularly known as “jailbreaking.” While jailbreaking primarily targets short-term noncompliance with predefined policies, we argue that a deeper vulnerability lies in altering an LLM’s fundamental axiomatic beliefs, such as mathematical or philosophical truths. In this work, we introduce GoodLiar, a reinforcement learning (RL)-based framework that generates deceptive contexts to systematically rewrite an LLM’s core logical or philosophical understandings. By incentivizing an RL agent to produce persuasive and coherent arguments, GoodLiar aims to induce persistent belief shifts, rather than merely influencing immediate judgments of factual truthfulness. %rather than one-off policy breaches. Our approach introduces DA-ILQL, a novel offline RL method that extends ILQL by integrating on-policy data and language exploration to enhance the language discovery and optimization. Through extensive evaluations on multiple LLMs, we show that deceptive contexts discovered by GoodLiar consistently outperform simple multi-turn prompting methods.