AINeutralarXiv – CS AI · May 17/10
🧠
Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
Researchers introduce CarryOnBench, a new interactive benchmark that evaluates whether large language models can recover helpfulness when users clarify benign intent across multi-turn conversations while maintaining safety. Testing 14 models with nearly 24,000 responses reveals that models significantly withhold information due to intent misinterpretation rather than knowledge limitations, and identifies three failure modes—utility lock-in, unsafe recovery, and repetitive recovery—that single-turn safety evaluations miss.