6 citations · 9 across the 15 of their papers we have counts for
17 papers
Aligned Data Can Induce Misalignment via Context Confusion
Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin +4
Large language models (LLMs) are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for preventing post-update misalignm…
Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning
Duygu Nur Yaldiz, Evangelia Spiliopoulou, Zheng Qi +3
Large language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confi…
Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
Yavuz Bakman, Duygu Nur Yaldiz, Eleni Triantafillou +3
Large Language Models (LLMs) are rarely static and are frequently updated in practice. A growing body of alignment research has shown that models initially deemed ``aligned'' can e…
Reject Only Critical Tokens: Pivot-Aware Speculative Decoding
Amir Ziashahabi, Yavuz Faruk Bakman, Duygu Nur Yaldiz +3
Speculative Decoding (SD) ensures that the output matches the target model's distribution exactly. However, we argue that this distribution matching requirement is too stringent an…
Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
Yavuz Bakman, Sungmin Kang, Zhiqi Huang +8
Uncertainty Quantification (UQ) research has primarily focused on closed-book factual question answering (QA), while contextual QA remains unexplored, despite its importance in rea…
Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directions
Sungmin Kang, Yavuz Faruk Bakman, Duygu Nur Yaldiz +2
The rapid advancement of large language models (LLMs) has transformed the landscape of natural language processing, enabling breakthroughs across a wide range of areas including qu…
Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
Ashwath Vaithinathan Aravindan, Abha Jha, Matthew Salaway +2
Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible…
TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sungmin Kang +9
Generative Large Language Models (LLMs)inevitably produce untruthful responses. Accurately predicting the truthfulness of these outputs is critical, especially in high-stakes setti…
Conformal Prediction Adaptive to Unknown Subpopulation Shifts
Nien-Shao Wang, Duygu Nur Yaldiz, Yavuz Faruk Bakman +1
Conformal prediction is widely used to equip black-box machine learning models with uncertainty quantification, offering formal coverage guarantees under exchangeable data. However…
Reconsidering LLM Uncertainty Estimation Methods in the Wild
Yavuz Bakman, Duygu Nur Yaldiz, Sungmin Kang +4
Large Language Model (LLM) Uncertainty Estimation (UE) methods have become a crucial tool for detecting hallucinations in recent years. While numerous UE methods have been proposed…
Un-considering Contextual Information: Assessing LLMs' Understanding of Indexical Elements
Metehan Oguz, Yavuz Bakman, Duygu Nur Yaldiz
Large Language Models (LLMs) have demonstrated impressive performances in tasks related to coreference resolution. However, previous studies mostly assessed LLM performance on core…
Backdoor Defense in Diffusion Models via Spatial Attention Unlearning
Abha Jha, Ashwath Vaithinathan Aravindan, Matthew Salaway +2
Text-to-image diffusion models are increasingly vulnerable to backdoor attacks, where malicious modifications to the training data cause the model to generate unintended outputs wh…
CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
Erum Mushtaq, Duygu Nur Yaldiz, Yavuz Faruk Bakman +4
Continual self-supervised learning (CSSL) learns a series of tasks sequentially on the unlabeled data. Two main challenges of continual learning are catastrophic forgetting and tas…
Do Not Design, Learn: A Trainable Scoring Function for Uncertainty Estimation in Generative LLMs
Duygu Nur Yaldiz, Yavuz Faruk Bakman, Baturalp Buyukates +5
Uncertainty estimation (UE) of generative large language models (LLMs) is crucial for evaluating the reliability of generated sequences. A significant subset of UE methods utilize…
MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs
Yavuz Faruk Bakman, Duygu Nur Yaldiz, Baturalp Buyukates +3
Generative Large Language Models (LLMs) are widely utilized for their excellence in various tasks. However, their tendency to produce inaccurate or misleading outputs poses a poten…
Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
Yavuz Faruk Bakman, Duygu Nur Yaldiz, Yahya H. Ezzeldin +1
Federated Learning (FL) has gained significant attraction due to its ability to enable privacy-preserving training over decentralized data. Current literature in FL mostly focuses…
Secure Federated Learning against Model Poisoning Attacks via Client Filtering
Duygu Nur Yaldiz, Tuo Zhang, Salman Avestimehr
Given the distributed nature, detecting and defending against the backdoor attack under federated learning (FL) systems is challenging. In this paper, we observe that the cosine si…