8 papers
Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
Rajesh Mangannavar, Zachary Coalson, Pranay Dugar +1
Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners require formal PDDL spe…
Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
Zachary Coalson, Bo Fang, Sanghyun Hong
Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in conversational LLMs: turn amplifi…
Discovering Universal Activation Directions for PII Leakage in Language Models
Leo Marchyok, Zachary Coalson, Sungho Keum +2
Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information (PII) leakage, are re…
Fail-Closed Alignment for Large Language Models
Zachary Coalson, Beth Sohler, Aiden Gabriel +1
We identify a structural weakness in current large language model (LLM) alignment: modern refusal mechanisms are fail-open. While existing approaches encode refusal behaviors acros…
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
Zachary Coalson, Huazheng Wang, Qingyun Wu +1
We study the robustness of data-centric methods to find neural network architectures, known as neural architecture search (NAS), against data poisoning. To audit this robustness, w…
IF-GUIDE: Influence Function-Guided Detoxification of LLMs
Zachary Coalson, Juhan Bae, Nicholas Carlini +1
We study how training data contributes to the emergence of toxic behaviors in large language models. Most prior work on reducing model toxicity adopts reactive approaches, such as…