7 citations · 9 across the 7 of their papers we have counts for
9 papers
Alignment Forecasting: Predicting Misalignment From Training Data
Chen Yueh-Han, Bruce W. Lee, Ilia Sucholutsky +1
Training a language model on data with a narrow flaw can sometimes make the model broadly misaligned. Inspecting the data at face value often does not settle whether it will emerge…
Reasoning Models Struggle to Control their Chains of Thought
Chen Yueh-Han, Robert McCarthy, Bruce W. Lee +5
Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what t…
Training Agents to Self-Report Misbehavior
Bruce W. Lee, Chen Yueh-Han, Tomek Korbak
Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by reinforcing the correct goals, but ali…
DEMONSTRATE: Zero-shot Language to Robotic Control via Multi-task Demonstration Learning
Rahel Rickenbach, Bruce Lee, René Zurbrügg +2
The integration of large language models (LLMs) with control systems has demonstrated significant potential in various settings, such as task completion with a robotic manipulator.…
Distillation Robustifies Unlearning
Bruce W. Lee, Addie Foote, Alex Infanger +6
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: t…
Programming Refusal with Conditional Activation Steering
Bruce W. Lee, Inkit Padhi, Karthikeyan Natesan Ramamurthy +4
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscrimina…
Inertia in Moral and Value Judgments of Large Language Models
Bruce W. Lee, Yeongheon Lee, Hyunsoo Cho
Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy is to assign a persona to the mod…
HyperCLOVA X Technical Report
Kang Min Yoo, Jaegeun Han, Sookyo In +393
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. H…
Instruction Tuning with Human Curriculum
Bruce W. Lee, Hyunsoo Cho, Kang Min Yoo
In this work, we (1) introduce Curriculum Instruction Tuning, (2) explore the potential advantages of employing diverse curriculum strategies, and (3) delineate a synthetic instruc…