3 papers
cs.IT2026
Language Modeling is Monotone Compression
Noam Mazor, Andrew Morgan, Rafael Pass
A long-standing hypothesis in artificial intelligence and neuroscience posits that intelligence is closely related to compression: the ability to compress information efficiently i…
cs.CR2026
Can we Watermark Low-Entropy LLM Outputs?
Noam Mazor, Andrew Morgan, Rafael Pass
A recent and exciting thread of work focuses on developing methods for watermarking the output of large language models (LLMs). We focus on provably undetectable watermarking-that…
cs.LG2017
Paradoxes in Fair Computer-Aided Decision Making
Andrew Morgan, Rafael Pass
Computer-aided decision making--where a human decision-maker is aided by a computational classifier in making a decision--is becoming increasingly prevalent. For instance, judges i…