6 citations · 15 across the 18 of their papers we have counts for
20 papers
Can Watermarking Techniques Help Prevent LLM Model Stealing?
Elette Boyle, MohammadTaghi Hajiaghayi, Keivan Rezaei +2
Model stealing attacks have recently been introduced, enabling the extraction of precise information from black-box commercial language models. In this work, we propose defense met…
SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
Mehrdad Saberi, Keivan Rezaei, Soheil Feizi
Large language models increasingly use external tools such as web search and document retrieval to solve information-intensive tasks. However, multi-hop tool use in complex tasks i…
Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
Yize Cheng, Chenrui Fan, Mahdi JafariRaviz +2
Large language models (LLMs) increasingly act as autonomous agents that must decide when to answer directly vs. when to invoke external tools. Prior work studying adaptive tool use…
Failing to Explore: Language Models on Interactive Tasks
Mahdi JafariRaviz, Keivan Rezaei, Arshia Soltani Moakhar +3
We evaluate language models on their ability to explore interactive environments under a limited interaction budget. We introduce three parametric tasks with controllable explorati…
Reasoning Under Uncertainty: Exploring Probabilistic Reasoning Capabilities of LLMs
Mobina Pournemat, Keivan Rezaei, Gaurang Sriramanan +5
Despite widespread success in language understanding and generation, large language models (LLMs) exhibit unclear and often inconsistent behavior when faced with tasks that require…
Revisiting the Past: Data Unlearning with Model State History
Keivan Rezaei, Mehrdad Saberi, Abhilasha Ravichander +1
Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model perfo…
Localizing Knowledge in Diffusion Transformers
Arman Zarei, Samyadeep Basu, Keivan Rezaei +3
Understanding how knowledge is distributed across the layers of generative models is crucial for improving interpretability, controllability, and adaptation. While prior work has e…
RePanda: Pandas-powered Tabular Verification and Reasoning
Atoosa Malemir Chegini, Keivan Rezaei, Hamid Eghbalzadeh +1
Fact-checking tabular data is essential for ensuring the accuracy of structured information. However, existing methods often rely on black-box models with opaque reasoning. We intr…
A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models
Zihao Lin, Samyadeep Basu, Mohammad Beigi +18
The rise of foundation models has transformed machine learning research, prompting efforts to uncover their inner workings and develop more efficient and reliable applications for…
RESTOR: Knowledge Recovery in Machine Unlearning
Keivan Rezaei, Khyathi Chandu, Soheil Feizi +3
Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, sev…
Ad Auctions for LLMs via Retrieval Augmented Generation
MohammadTaghi Hajiaghayi, Sébastien Lahaie, Keivan Rezaei +1
In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without comprom…
Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings
Arman Zarei, Keivan Rezaei, Samyadeep Basu +4
Text-to-image diffusion-based generative models have the stunning ability to generate photo-realistic images and achieve state-of-the-art low FID scores on challenging image genera…
On Mechanistic Knowledge Localization in Text-to-Image Generative Models
Samyadeep Basu, Keivan Rezaei, Priyatham Kattakinda +5
Identifying layers within text-to-image models which control visual attributes can facilitate efficient model editing through closed-form updates. Recent work, leveraging causal tr…
Online Advertisements with LLMs: Opportunities and Challenges
Soheil Feizi, MohammadTaghi Hajiaghayi, Keivan Rezaei +1
This paper explores the potential for leveraging Large Language Models (LLM) in the realm of online advertising systems. We introduce a general framework for LLM advertisement, con…
Regret Analysis of Repeated Delegated Choice
MohammadTaghi Hajiaghayi, Mohammad Mahdavi, Keivan Rezaei +1
We present a study on a repeated delegated choice problem, which is the first to consider an online learning variant of Kleinberg and Kleinberg, EC'18. In this model, a principal i…
PRIME: Prioritizing Interpretability in Failure Mode Extraction
Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri +1
In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. Existing works address this problem by…
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei +4
In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materia…
Delegating to Multiple Agents
MohammadTaghi Hajiaghayi, Keivan Rezaei, Suho Shin
We consider a multi-agent delegation mechanism without money. In our model, given a set of agents, each agent has a fixed number of solutions which is exogenous to the mechanism, a…
Text-To-Concept (and Back) via Cross-Model Alignment
Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi +1
We observe that the mapping between an image's representation in one model to its representation in another can be learned surprisingly well with just a linear layer, even across d…
Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
Keivan Rezaei, Kiarash Banihashem, Atoosa Chegini +1
In data poisoning attacks, an adversary tries to change a model's prediction by adding, modifying, or removing samples in the training data. Recently, ensemble-based approaches for…