Skip to yearly menu bar Skip to main content


Poster

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers

Muhammed Emrullah Ildiz · Yixiao HUANG · Yingcong Li · Ankit Singh Rawat · Samet Oymak

Hall C 4-9 #408
[ ] [ Paper PDF ]
Thu 25 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

Modern language models rely on the transformer architecture and attention mechanism to perform language understanding and text generation. In this work, we study learning a 1-layer self-attention model from a set of prompts and the associated outputs sampled from the model. We first establish a formal link between the self-attention mechanism and Markov models under suitable conditions: Inputting a prompt to the self-attention model samples the output token according to a context-conditioned Markov chain (CCMC). CCMC is obtained by weighing the transition matrix of a standard Markov chain according to the sufficient statistics of the prompt/context. Building on this formalism, we develop identifiability/coverage conditions for the data distribution that guarantee consistent estimation of the latent model under a teacher-student setting and establish sample complexity guarantees under IID data. Finally, we study the problem of learning from a single output trajectory generated in response to an initial prompt. We characterize a winner-takes-all phenomenon where the generative process of self-attention evolves to sampling from a small set of winner tokens that dominate the context window. This provides a mathematical explanation to the tendency of modern LLMs to generate repetitive text.

Chat is not available.