6 accepted papers
Instruction following in LLMs captures models' ability to change their visible behaviors as requested by users. Instead, we study models' ability to control their chain-of-thought (CoT). This capability -- CoT controllability -- is undesirable because it could allow models to suppress signs of misbe…
Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on unwanted information. This shows that training a model can drastica…
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selective responses are essential, such as content modera…
As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values. Tracking the emergence of goals and values has proven a longstanding problem, and despite much interest over the years it…
In this work, we (1) introduce Curriculum Instruction Tuning, (2) explore the potential advantages of employing diverse curriculum strategies, and (3) delineate a synthetic instruction-response generation framework that complements our theoretical approach. Distinct from the existing instruction tun…
We report two essential improvements in readability assessment: 1. three novel features in advanced semantics and 2. the timely evidence that traditional ML models (e.g. Random Forest, using handcrafted features) can combine with transformers (e.g. RoBERTa) to augment model performance. First, we ex…