Please refer to Google Scholar for all my publications.

Published

Neither Valid Nor Reliable? Investigating the Use of LLMs as Judges
Chehbouni Khaoula, Haddou Mohammed, Cheung CK Jackie, Farnadi Golnoosh The Thirty-Ninth Annual Conference on Neural Information Processing Systems Position Paper Track 2025 [paper]

Beyond the Safety Bundle: Auditing the Helpful and Harmless Dataset
Chehbouni* Khaoula and Colaço Carr* Jonathan, More Yash, Cheung CK Jackie, Farnadi Golnoosh Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics — Oral [paper]

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
Chehbouni Khaoula, Roshan Megha, Ma Emmanuel, Andrew Wei Futian, Taik Afaf, Cheung Jackie CK, Farnadi Golnoosh
Findings of the Association for Computational Linguistics ACL 2024 — Poster
[paper]

Enhancing privacy in the early detection of sexual predators through federated learning and differential privacy
Chehbouni Khaoula, De Cock Martine, Caporossi Gilles, Taïk Afaf, Rabbany Reihaneh, Farnadi Golnoosh
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence AAAI 2025 — Oral
[paper]

Forthcoming

LLJ Cards: Best Practices for the Use of LLMs as Judges
Chehbouni Khaoula, Medjdoub Melina, Carichon Florian, Farnadi* Golnoosh, Cheung* CK Jackie

From Infrastructure to Interface: the AI Value Chain Drives LLM Homogenization
Chehbouni Khaoula, Chataigner Cléa, Ganesh Prakhar, Piantanida Pablo, Cheung CK Jackie, Farnadi Golnoosh