# How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT's Attention

arXiv: https://arxiv.org/abs/2011.00943 · HTML: https://mlsanity.com/paper/2011.00943/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation](https://mlsanity.com/paper/2202.07471/) (2022)
- [ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization](https://mlsanity.com/paper/2208.14286/) (2022)
- [Dual-side Sparse Tensor Core](https://mlsanity.com/paper/2105.09564/) (2021)
- [Interpretability Illusions in the Generalization of Simplified Models](https://mlsanity.com/paper/2312.03656/) (2023)
- [Transkimmer: Transformer Learns to Layer-wise Skim](https://mlsanity.com/paper/2205.07324/) (2022)
- [Block-Skim: Efficient Question Answering for Transformer](https://mlsanity.com/paper/2112.08560/) (2021)
- [M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type](https://mlsanity.com/paper/2502.18755/) (2025)
- [Analyzing Semantic Change through Lexical Replacements](https://mlsanity.com/paper/2404.18570/) (2024)
- [Analysis of Argument Structure Constructions in the Large Language Model BERT](https://mlsanity.com/paper/2408.04270/) (2024)
- [AttentionMix: Data augmentation method that relies on BERT attention mechanism](https://mlsanity.com/paper/2309.11104/) (2023)

## Abstract (arXiv)

Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism. As most of the research focus on probing tasks or hidden states, previous works have found some primitive patterns of attention head behavior by heuristic analytical methods, but a more systematic analysis specific on the attention patterns still remains primitive. In this work, we clearly cluster the attention heatmaps into significantly different patterns through unsupervised clustering on top of a set of proposed features, which corroborates with previous observations. We further study their corresponding functions through analytical study. In addition, our proposed features can be used to explain and calibrate different attention heads in Transformer models.