Search Results for author:
Found 2 papers, 2 papers with code
Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks
However, we highlight two issues in previous backdoor learning evaluations: (1) The differences between real-world scenarios (e. g. releasing poisoned datasets or models) are neglected, and we argue that each scenario has its own constraints and concerns, thus requires specific evaluation protocols; (2) The evaluation metrics only consider whether the attacks could flip the models' predictions on poisoned samples and retain performances on benign samples, but ignore that poisoned samples should also be stealthy and semantic-preserving.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
