Malevolence Attacks Against Pretrained Dialogue Models.

@inproceedings{ren-2025-malevolence, author = {Pengjie Ren and Ruiqi Li and Zhaochun Ren and Zhumin Chen and Maarten de Rijke and Yangjun Zhang}, editor = {Claudia Hauff and Craig Macdonald and Dietmar Jannach and Gabriella Kazai and Franco Maria Nardini and Fabio Pinelli and Fabrizio Silvestri and Nicola Tonellotto}, title = {{Malevolence Attacks Against Pretrained Dialogue Models}}, booktitle = {{Advances in Information Retrieval - 47th European Conference on Information Retrieval, ECIR 2025, Lucca, Italy, April 6-10, 2025, Proceedings, Part I}}, series = {Lecture Notes in Computer Science}, volume = {15572}, pages = {372--388}, publisher = {Springer}, year = {2025}, url = {https://doi.org/10.1007/978-3-031-88708-6_24}, doi = {https://doi.org/10.1007/978-3-031-88708-6_24} }