Information Theory for Language

Entropy, cross-entropy, KL, perplexity, calibration, and language modelling as compression.

16concepts
161flashcards
126minutes of reading
  1. 01 Calibration of Language Models What it means for a model's stated confidence to be trustworthy, why pretrained next-token probabilities start out well calibrated and RLHF quietly breaks that, and how to actually measure the gap. advanced 9m 6 cards
  2. 02 Channel Capacity and the Noisy Channel Shannon's capacity theorem, why it says reliable communication is possible at any rate below capacity and impossible above it, and why the noisy-channel decomposition keeps reappearing in language modelling. advanced 8m 20 cards
  3. 03 Kolmogorov Complexity and MDL The shortest program that outputs a string is the ultimate measure of its information content, why it is uncomputable, and how minimum description length turns that uncomputable ideal into a usable model selection principle. advanced 8m 20 cards
  4. 04 Language Modelling as Compression Every autoregressive language model is, exactly and not metaphorically, a lossless compressor; arithmetic coding is the bridge, and that equivalence is what let a text-only LLM out-compress PNG and FLAC on images and audio. advanced 10m 6 cards
  5. 05 Mutual Information and Representations The information-theoretic quantity that measures how much one variable tells you about another, why it is the right lens for judging whether a learned representation actually captured something, and why estimating it in high dimensions is notoriously hard. advanced 9m 6 cards
  6. 06 Rate-Distortion Theory The theory of how few bits a source needs when perfect reconstruction is not required, why every compression decision in an LLM stack is a point on one curve, and what the curve's shape tells you. advanced 9m 20 cards
  7. 07 The Softmax Bottleneck Why a standard softmax output layer is a low-rank approximation to the true distribution of language, the "bottleneck" that caps what any single softmax can express, and the mixture trick that breaks it. advanced 9m 6 cards
  8. 08 Typical Sets and the AEP Why almost all probability mass sits on a vanishingly small set of sequences that are individually unremarkable, and why the most likely sequence is usually not a typical one. advanced 8m 20 cards
  9. 09 f-Divergences Beyond KL KL is one member of a family generated by a convex function, the choice of member decides whether your model covers the data or collapses onto a mode, and some tasks need a divergence that is not in the family at all. advanced 8m 20 cards