activity
20232025
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2025

On Union-Closedness of Language Generation

Steve Hanneke, Amin Karbasi, Anay Mehrotra +1

We investigate language generation in the limit - a model by Kleinberg and Mullainathan [NeurIPS 2024] and extended by Li, Raman, and Tewari [COLT 2025]. While Kleinberg and Mullai…

cs.LG2025

(Im)possibility of Automated Hallucination Detection in Large Language Models

Amin Karbasi, Omar Montasser, John Sous +1

Is automated hallucination detection possible? In this work, we introduce a theoretical framework to analyze the feasibility of automatically detecting hallucinations produced by l…

cs.LG2025

Adversarial Reasoning at Jailbreaking Time

Mahdi Sabbaghi, Paul Kassianik, George Pappas +3

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, mea…

cs.LG2024

Extracting Memorized Training Data via Decomposition

Ellen Su, Anu Vellore, Amy Chang +4

The widespread use of Large Language Models (LLMs) in society creates new information security challenges for developers, organizations, and end-users alike. LLMs are trained on la…

cs.LG2024

Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models

Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou +3

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks.…

cs.LG2024

On the Computational Landscape of Replicable Learning

Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas +1

We study computational aspects of algorithmic replicability, a notion of stability introduced by Impagliazzo, Lei, Pitassi, and Sorrell [2022]. Motivated by a recent line of work t…