2 papers
cs.CL2026
Consistency Training Can Entrench Misalignment
David Demitri Africa, Arathi Mani
Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures. Such methods are simple, scalable, and largely label-free, but thei…
cs.LG2025
Async Control: Stress-testing Asynchronous Control Measures for LLM Agents
Asa Cooper Stickland, Jan Michelfeit, Arathi Mani +6
LLM-based software engineering agents are increasingly used in real-world development tasks, often with access to sensitive data or security-critical codebases. Such agents could i…