22 citations · 28 across the 4 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Haiku to Opus in Just 10 bits: LLMs Unlock Large Compression Gains
Roy Rinberg, Annabelle Michael Carrell, Simon Henniger +2
We study the compression of LLM-generated text across lossless and lossy regimes, characterizing a compression-compute frontier where more compression is possible at the cost of mo…
cs.LG2025★ 6 cited
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
Alexandra Souly, Javier Rando, Ed Chapman +10
Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoni…
cs.LG2021★ 22 cited
Poisoning the Unlabeled Dataset of Semi-Supervised Learning
Nicholas Carlini
Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach w…