7 papers
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Vamshi Krishna Bonagiri, Ponnurangam Kumaragurum, Khanh Nguyen +1
As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While uncertainty quantification is w…
Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards
Sarah Liaw, Benjamin Plaut
In high-stakes AI applications, even a single action can cause irreparable damage. However, nearly all of sequential decision-making theory assumes that all errors are recoverable…
Safety Training Persists Through Helpfulness Optimization in LLM Agents
Benjamin Plaut
Safety post-training has been studied extensively in single-step "chat" settings where safety typically refers to refusing harmful requests. We study an "agentic" (i.e., multi-step…
YRC-Bench: A Benchmark for Learning to Coordinate with Experts
Mohamad H. Danesh, Nguyen X. Khanh, Tu Trinh +1
When deployed in the real world, AI agents will inevitably face challenges that exceed their individual capabilities. A critical component of AI safety is an agent's ability to rec…
Safe Learning Under Irreversible Dynamics via Asking for Help
Benjamin Plaut, Juan Liévano-Karim, Hanlin Zhu +1
Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, w…
Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
Benjamin Plaut, Nguyen X. Khanh, Tu Trinh
We study 15 large language models (LLMs) fine-tuned for chat and find that their maximum softmax probabilities (MSPs) are consistently miscalibrated on multiple-choice Q&A. However…