Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences, University of Chinese Academy of Sciences
7
0
8
EVIL-Detect outperforms existing methods by achieving a macro-F1 score of 0.8888 in detecting LLM-generated text, even under challenging conditions.
EchoPrompt reveals that by restoring latent prompts, we can significantly enhance the detection of LLM-generated text, achieving state-of-the-art results without any training.
LLM agent harnesses are surprisingly vulnerable, but weaving security directly into the agent lifecycle can slash attack success by 42% without sacrificing utility.
LLMs can now perform entity alignment with greater interpretability and efficiency thanks to a new agent-based approach that structures the reasoning process.
LLMs often invoke irrelevant tools just because the query structure *fits* the tool's parameters, revealing a surprising and widespread flaw in their reasoning.
Forget visit order: modeling item-specific purchase cadences with calendar time unlocks significant gains in next-basket repurchase prediction, even at production scale.
A novel ensemble method substantially improves the reliability of detecting Chinese LLM-generated text, even against adversarial examples.
