# Every word counts: A multilingual analysis of individual human alignment with model attention

arXiv: https://arxiv.org/abs/2210.04963 · HTML: https://mlsanity.com/paper/2210.04963/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 5 Oct 2022.

## Builds on (most cited first, 10 of 10)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension](https://mlsanity.com/paper/2010.06396/) (2020)
- [Multilingual Language Models Predict Human Reading Behavior](https://mlsanity.com/paper/2104.05433/) (2021)
- [CogniVal: A Framework for Cognitive Word Embedding Evaluation](https://mlsanity.com/paper/1909.09001/) (2019)
- [Relative Importance in Sentence Processing](https://mlsanity.com/paper/2106.03471/) (2021)
- [Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?](https://mlsanity.com/paper/2205.10226/) (2022)
- [Predicting Native Language from Gaze](https://mlsanity.com/paper/1704.07398/) (2017)

## Built on by (most cited first, 4 of 4)

- [WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset](https://mlsanity.com/paper/2303.17876/) (2023)
- [Longer Fixations, More Computation: Gaze-Guided Recurrent Neural Networks](https://mlsanity.com/paper/2311.00159/) (2023)
- [Cross-Lingual Transfer of Cognitive Processing Complexity](https://mlsanity.com/paper/2302.12695/) (2023)
- [Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations](https://mlsanity.com/paper/2402.19133/) (2024)

## Abstract (arXiv)

Human fixation patterns have been shown to correlate strongly with Transformer-based attention. Those correlation analyses are usually carried out without taking into account individual differences between participants and are mostly done on monolingual datasets making it difficult to generalise findings. In this paper, we analyse eye-tracking data from speakers of 13 different languages reading both in their native language (L1) and in English as language learners (L2). We find considerable differences between languages but also that individual reading behaviour such as skipping rate, total reading time and vocabulary knowledge (LexTALE) influence the alignment between humans and models to an extent that should be considered in future studies.