1 citations · 2 across the 9 of their papers we have counts for
5 papers · 1 filter
Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
Sarah Ball, Niki Hasrati, Alexander Robey +4
Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input prompts, elicit disallowed cont…
Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning
Yushi Yang, Shreyansh Padarha, Sarah Ball +2
Agentic reinforcement learning (RL) trains large language models to use tools, but its impact on alignment is poorly understood. We study how agentic RL for search affects the alig…
Don't Walk the Line: Boundary Guidance for Filtered Generation
Sarah Ball, Andreas Haupt
Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs. A common strategy is to fine-tune the generator to reduce the probabil…
On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
Sarah Ball, Greg Gluch, Shafi Goldwasser +3
With the increased deployment of large language models (LLMs), one concern is their potential misuse for generating harmful content. Our work studies the alignment challenge, with…
Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction
Sarah Ball, Simeon Allmendinger, Frauke Kreuter +1
Generative AI (GenAI) is increasingly used in survey contexts to simulate human preferences. While many research endeavors evaluate the quality of synthetic GenAI data by comparing…