Duygu Nur Yaldiz

24 papers A* 1B 1Journal 16Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning. CoRR Duygu Nur Yaldiz, Evangelia Spiliopoulou, Zheng Qi, Siddharth Varia, Srikanth Doss, Nikolaos Pappas
2026	J	`jnl`	Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment. CoRR Yavuz Faruk Bakman, Duygu Nur Yaldiz, Salman Avestimehr, Sai Praneeth Karimireddy
2025	J	`jnl`	Backdoor Defense in Diffusion Models via Spatial Attention Unlearning. CoRR Abha Jha, Ashwath Vaithinathan Aravindan, Matthew Salaway, Atharva Sandeep Bhide, Duygu Nur Yaldiz
2025	J	`jnl`	Conformal Prediction Adaptive to Unknown Subpopulation Shifts. CoRR Nien-Shao Wang, Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sai Praneeth Karimireddy
2025	—	`conf`	Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs. NAACL (Findings) Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates, Chenyang Tao, Anil Ramakrishna, Dimitrios Dimitriadis, Jieyu Zhao, Salman Avestimehr
2025	—	`conf`	Reconsidering LLM Uncertainty Estimation Methods in the Wild. ACL (1) Yavuz Faruk Bakman, Duygu Nur Yaldiz, Sungmin Kang, Tuo Zhang, Baturalp Buyukates, Salman Avestimehr, Sai Praneeth Karimireddy
2025	J	`jnl`	Reconsidering LLM Uncertainty Estimation Methods in the Wild. CoRR Yavuz Faruk Bakman, Duygu Nur Yaldiz, Sungmin Kang, Tuo Zhang, Baturalp Buyukates, Salman Avestimehr, Sai Praneeth Karimireddy
2025	J	`jnl`	Reject Only Critical Tokens: Pivot-Aware Speculative Decoding. CoRR Amir Ziashahabi, Yavuz Faruk Bakman, Duygu Nur Yaldiz, Mostafa El-Khamy, Sai Praneeth Karimireddy, Salman Avestimehr
2025	J	`jnl`	Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation. CoRR Ashwath Vaithinathan Aravindan, Abha Jha, Matthew Salaway, Atharva Sandeep Bhide, Duygu Nur Yaldiz
2025	—	`conf`	TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs. EMNLP (System Demonstrations) Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sungmin Kang, Alperen Özis, Hayrettin Eren Yildiz, Mitash Ashish Shah, Zhiqi Huang, Anoop Kumar, Alfy Samuel, Daben Liu, Sai Praneeth Karimireddy, Salman Avestimehr
2025	J	`jnl`	TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs. CoRR Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sungmin Kang, Alperen Özis, Hayrettin Eren Yildiz, Mitash Ashish Shah, Zhiqi Huang, Anoop Kumar, Alfy Samuel, Daben Liu, Sai Praneeth Karimireddy, Salman Avestimehr
2025	—	`conf`	Un-considering Contextual Information: Assessing LLMs' Understanding of Indexical Elements. ACL (Findings) Metehan Oguz, Yavuz Faruk Bakman, Duygu Nur Yaldiz
2025	J	`jnl`	Un-considering Contextual Information: Assessing LLMs' Understanding of Indexical Elements. CoRR Metehan Oguz, Yavuz Faruk Bakman, Duygu Nur Yaldiz
2025	J	`jnl`	Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions. CoRR Sungmin Kang, Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Salman Avestimehr
2025	J	`jnl`	Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering. CoRR Yavuz Faruk Bakman, Sungmin Kang, Zhiqi Huang, Duygu Nur Yaldiz, Catarina G. Belém, Chenyang Zhu, Anoop Kumar, Alfy Samuel, Salman Avestimehr, Daben Liu, Sai Praneeth Karimireddy
2024	—	`conf`	CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning. ECCV (80) Erum Mushtaq, Duygu Nur Yaldiz, Yavuz Faruk Bakman, Jie Ding, Chenyang Tao, Dimitrios Dimitriadis, Salman Avestimehr
2024	J	`jnl`	CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning. CoRR Erum Mushtaq, Duygu Nur Yaldiz, Yavuz Faruk Bakman, Jie Ding, Chenyang Tao, Dimitrios Dimitriadis, Salman Avestimehr
2024	J	`jnl`	Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs. CoRR Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates, Chenyang Tao, Anil Ramakrishna, Dimitrios Dimitriadis, Salman Avestimehr
2024	A*	`conf`	Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning. ICLR Yavuz Faruk Bakman, Duygu Nur Yaldiz, Yahya H. Ezzeldin, Salman Avestimehr
2024	—	`conf`	MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs. ACL (1) Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Chenyang Tao, Dimitrios Dimitriadis, Salman Avestimehr
2024	J	`jnl`	MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs. CoRR Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Chenyang Tao, Dimitrios Dimitriadis, Salman Avestimehr
2024	B	`conf`	Predicting Uncertainty of Generative LLMs with MARS: Meaning-Aware Response Scoring. ISIT Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates, Salman Avestimehr, Chenyang Tao, Dimitrios Dimitriadis
2023	J	`jnl`	Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning. CoRR Yavuz Faruk Bakman, Duygu Nur Yaldiz, Yahya H. Ezzeldin, Salman Avestimehr
2023	J	`jnl`	Secure Federated Learning against Model Poisoning Attacks via Client Filtering. CoRR Duygu Nur Yaldiz, Tuo Zhang, Salman Avestimehr