Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis

TL;DR

This paper introduces TAPPA, a unifying framework that explains diverse attention patterns in large language models by analyzing their mathematical properties from a temporal perspective, improving understanding and inference efficiency.

Contribution

TAPPA provides a unified mathematical analysis of attention patterns, linking their regularities to query self-similarity, and applies these insights to enhance LLM inference tasks.

Findings

Predictable attention patterns correlate with query self-similarity.

TAPPA's metrics improve KV cache compression performance.

Insights from TAPPA enhance LLM pruning methods.

Abstract

Attention patterns play a crucial role in both training and inference of large language models (LLMs). Prior works have identified individual patterns such as retrieval heads, sink heads, and diagonal traces, yet these observations remain fragmented and lack a unifying explanation. To bridge this gap, we introduce \textbf{Temporal Attention Pattern Predictability Analysis (TAPPA), a unifying framework that explains diverse attention patterns by analyzing their underlying mathematical formulations} from a temporally continuous perspective. TAPPA both deepens the understanding of attention behavior and guides inference acceleration approaches. Specifically, TAPPA characterizes attention patterns as predictable patterns with clear regularities and unpredictable patterns that appear effectively random. Our analysis further reveals that this distinction can be explained by the degree of query self-similarity along the temporal dimension. Focusing on the predictable patterns, we further provide a detailed mathematical analysis of three representative cases through the joint effect of queries, keys, and Rotary Positional Embeddings (RoPE). We validate TAPPA by applying its insights to KV cache compression and LLM pruning tasks. Across these tasks, a simple metric motivated by TAPPA consistently improves performance over baseline methods. The code is available at https://github.com/MIRALab-USTC/LLM-TAPPA.