Tag: sampling
All the articles with the tag "sampling".
Decoding: From a Distribution to Text
Updated:A language model outputs a probability for every possible next token; decoding is the policy that turns that into text. Greedy and beam search, temperature derived, top-k, top-p and min-p on a real model's distributions, the order the steps run in, repetition penalties, and why the same prompt can give different text. Each one measured with Qwen2.5-1.5B on twenty paragraphs of this blog, against what a person actually wrote next.
Watermarking LLM Text: A Signal Hidden in the Sampling
Updated:Sampling leaves slack: many tokens would do at most steps. A keyed bias toward a pseudo-random green list spends that slack on a signature anyone with the key can test for, with no access to the model. The green-list scheme and its z-test derived and worked, how many tokens detection needs, the scheme run on a real 1.5B model at four bias strengths with its cost in likelihood, why low-entropy text resists it, what substitution and paraphrase do to it, distortion-free schemes (Aaronson's Gumbel trick, SynthID-Text's tournament), and why post-hoc AI-text detectors are a different and weaker thing.