Papers
arxiv:2606.24077

Sentence-Level Contextual Entrainment in Large Language Models

Published on Jun 23
Authors:
,

Abstract

Sentence-level contextual entrainment exists in large language models, where prompt sentences increase in probability during inference, and this phenomenon is controlled by a small subset of attention heads.

Contextual entrainment, which is a newly discovered phenomenon in large language models (LLMs), refers to the tendency of a model to assign higher probabilities to tokens that appear in its context. In this work, we extend this phenomenon from the token level to the sentence level by examining the per-token mean log-probability of a sentence instead of the probabilities of individual tokens. We investigate sentence-level contextual entrainment across 26 LLMs from seven families and two datasets, which cover both subjective and objective tasks. We find that sentence-level contextual entrainment exists. This means that the sentences in the prompt (even if they are counterfactual statements) can significantly increase their probability during model inference time. As the model size increases, contextual entrainment gradually decreases. We also find that contextual entrainment is controlled by 2% to 4% of the attention heads. Turning off these attention heads can effectively mitigate contextual entrainment without hurting the model's performance.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.24077
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.24077 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.24077 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.24077 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.