Nathalie Baracaldo

PhD student, University of Pittsburgh

Researcher, IBM, International Business Machines

Joined

July 2019

Names

Nathalie Baracaldo

Emails

****@us.ibm.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

PhD student

University of Pittsburgh (pitt.edu)

Present

Researcher

IBM, International Business Machines (us.ibm.com)

2016 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

AI Security and privacy

Present

Publications

Entropy-Aware On-Policy Distillation of Language Models
Woogyeol Jin, Taywon Min, Yongjin Yang, Swanand Ravindra Kadhe, Yi Zhou, Dennis Wei, Nathalie Baracaldo, Kimin Lee
- SPOT
- Readers: Everyone
GneissWeb: Preparing High Quality Data for LLMs at Scale
Hajar Emami Gohari, Swanand Ravindra Kadhe, Yousaf Shah, Constantin M Adam, Abdulhamid Adebayo, Praneet Adusumilli, Farhan Ahmed, Nathalie Baracaldo, Santosh Subhashrao Borse, Yuan-Chi Chang, Xuan-Hong Dang, Nirmit Desai, Revital Eres, Ran Iwamoto, Alexei A. Karve, Yan Koyfman, Wei-Han Lee, Changchang Liu, Boris Lublinsky, Takuya Ohko et al. (12 additional authors not shown)
- ICLR 2026 Poster
- Readers: Everyone
An Efficient and Modular Framework for Targeted Harm Mitigation in LLMs
Roberto Campbell, Momin Abbas, Muneeza Azmat, Michał Ulewicz, Raya Horesh, Kristjan Greenewald, Rogério Abreu de Paula, Nathalie Baracaldo
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation
Jinghan Jia, Hadi Reisizadeh, Chongyu Fan, Nathalie Baracaldo, Mingyi Hong, Sijia Liu
- Submitted to ICLR 2026
- Readers: Everyone
Rethinking Unlearning for Large Reasoning Models
Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
- MUGen @ ICML 2025 Poster
- Readers: Everyone
The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
Raj Sanjay Shah, Jing Huang, Keerthiram Murugesan, Nathalie Baracaldo, Diyi Yang
- COLM 2025
- Readers: Everyone
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu
- ICML 2025 poster
- Readers: Everyone
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
Jinghan Jia, Jiancheng Liu, Yihua Zhang, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
- CPAL 2025 (Recent Spotlight Track)
- Readers: Everyone
MAP: Multi-Human-Value Alignment Palette
Xinran Wang, Qi Le, Ammar Ahmed, Enmao Diao, Yi Zhou, Nathalie Baracaldo, Jie Ding, Ali Anwar
- ICLR 2025 Oral
- Readers: Everyone
Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning
Heshan Devaka Fernando, Han Shen, Parikshit Ram, Yi Zhou, Horst Samulowitz, Nathalie Baracaldo, Tianyi Chen
- Submitted to ICLR 2025
- Readers: Everyone

View all 19 publications

Co-Authors

View all 93 co-authors