Yufei Xia

RAGSentinel can filter out adversarial documents with high precision, ensuring that retrieval-augmented generation systems remain robust against sophisticated attacks.

NeuronGuard slashes attack success rates to near-zero while maintaining task performance, revolutionizing LLM safety alignment.

AgentLocate reveals not just which agent failed, but also the critical moment when the system first went off track, outperforming traditional methods in efficiency and accuracy.

LLMs can misclassify harmless rephrasings as critical errors, but a new lightweight metric outperforms larger models in clinical significance evaluation.

Encoder-free speech modeling can rival traditional methods, challenging the necessity of dedicated speech encoders in LLM architectures.