Papers by Meina Chen
Exploiting Prompt-induced Confidence for Black-Box Attacks on LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are vulnerable to adversarial attacks even in strict black-box settings with only hard-label feedback. |
| Approach: | They propose a black-box framework that leverages prompt-induced confidence as an auxiliary signal to guide attacks. |
| Outcome: | The proposed framework improves the attack success rate and query efficiency while maintaining semantic fidelity. |
A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling (P19-1)
Copied to clipboard
| Challenge: | Existing models for slot filling and intent detection lack bi-directional interrelated connections between the intent and slots. |
| Approach: | They propose a bi-directional interrelated model for slot filling and intent detection that uses an SF-ID network to establish direct connections between the two tasks to promote each other mutually. |
| Outcome: | The proposed model improves on ATIS and Snips datasets in sentence-level semantic frame accuracy and improves performance on the two tasks. |