2 papers
cs.LG2026
Barriers to Counterfactual Credit Attribution for Autoregressive Models
Aloni Cohen, Chenhao Zhang
Generative AI disrupts the practice of giving credit to work that came before. Ideally, a generative model would give credit to any work on which its output depends in a significan…
cs.CR2024
Watermarking Language Models for Many Adaptive Users
Aloni Cohen, Alexander Hoover, Gabe Schoenbach
We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a…