Xinfeng Li

Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to harmful prompts at the expense of overcautious behavior, leading models to incorrectly refuse benign requests. A key goal of safe alignment is ther...

The efficiency of multi-agent systems driven by large language models (LLMs) largely hinges on their communication topology. However, designing an optimal topology is a non-trivial challenge, as it requires balancing competing objectives such as task performance, communication cost, and robustnes...

As text-to-music models gain widespread adoption, the prompts used to guide these systems have become valuable intellectual property. This shift has given rise to a new form of attack: prompt stealing, aiming to reconstruct the high-value prompts that guide the music generation. However, unlike p...

Large language models (LLMs) have shown great potential in multi-disciplinary team (MDT) medical consultations. However, long, multi-round, multi-role interaction trajectories inevitably lead to severe information dilution and context window overload, triggering context collapse which destabilize...