Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze? (2022.acl-long)
Copied to clipboard
| Challenge: | We compare attention functions in pre-trained language models to human eye fixation patterns during task-specific reading tasks. |
| Approach: | They compare attention functions in large-scale pre-trained language models to classical cognitive models of human attention by using a dataset with eye-tracking recordings of native speakers of English. |
| Outcome: | The proposed model is as predictive of human eye fixation patterns as classical cognitive models of human attention. |
Similar Papers
Every word counts: A multilingual analysis of individual human alignment with model attention (2022.aacl-short)
Copied to clipboard
| Challenge: | Using eye-tracking data, fixation durations are often not considered in generalisation studies because of individual differences. |
| Approach: | They analyse eye-tracking data from speakers of 13 different languages reading . they find significant differences between languages but also individual reading behaviour . |
| Outcome: | The proposed model can be used to improve the generalization of ML models and allow for more personalized and fair applications. |
From Human Reading to NLM Understanding: Evaluating the Role of Eye-Tracking Data in Encoder-Based Models (2025.acl-long)
Copied to clipboard
| Challenge: | integrating eye-tracking features into Neural Language Models does not degrade downstream task performance, enhances alignment between model attention and human attention patterns, and compresses the embedding space. |
| Approach: | They used eye-gaze data from the Ghent Eye-Tracking Corpus to investigate how integrating knowledge of human reading behavior impacts Neural Language Models. |
| Outcome: | The proposed approach does not degrade downstream task performance, enhances alignment between model attention and human attention patterns, and compresses the embedding space. |
Measuring the Impact of (Psycho-)Linguistic and Readability Features and Their Spill Over Effects on the Prediction of Eye Movement Patterns (2022.acl-long)
Copied to clipboard
| Challenge: | Existing work to predict gaze patterns during naturalistic reading has not been conducted on general text characteristics. |
| Approach: | They propose to use two eye-tracking corpora of naturalistic reading and two language models to test their performance. |
| Outcome: | The proposed models predict eye-tracking measures during naturalistic reading and language processing. |
Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal (2022.emnlp-main)
Copied to clipboard
| Challenge: | Transformer-based large language models are trained to make predictions about the next word by aggregating representations of previous tokens through their self-attention mechanism. |
| Approach: | They propose an entropy-based predictor that quantifies the diffuseness of self-attention and a distance-based one that captures the incremental change in attention patterns across timesteps. |
| Outcome: | The proposed models perform better over a rigorous baseline including GPT-2 surprisal than previous models that used entropy-based predictors and distance-based ones. |
Multilingual Language Models Predict Human Reading Behavior (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that cognitively motivated "attention" mechanism in neural models is not a good indicator for relative importance. |
| Approach: | They compare the performance of language-specific and multilingual pretrained transformer models to predict reading time measures reflecting natural human sentence processing. |
| Outcome: | The proposed models predict reading time measures on Dutch, English, German, and Russian texts. |
Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words? (2020.acl-main)
Copied to clipboard
| Challenge: | Attention-based models have been claimed to add interpretability, but little is known about the actual relationships between machine and human attention. |
| Approach: | They conduct the first quantitative assessment of human versus computational attention mechanisms for the text classification task. |
| Outcome: | The proposed models are compared against machine attention maps on a publicly available YELP dataset. |
Scaling in Cognitive Modelling: a Multilingual Approach to Human Reading Times (2023.acl-short)
Copied to clipboard
| Challenge: | Neural language models provide conditional probability distributions over the lexicon that are predictive of human processing times. |
| Approach: | They propose to use a transformer-based model to generate probabilistic estimates that are less predictive of early eye-tracking measurements reflecting lexical access and early semantic integration. |
| Outcome: | The proposed models show that larger models capture late eye-tracking measurements that reflect the full integration of a word into the current language context. |
Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have shown strong abilities to understand natural language, but how these factors affect the models’ language perception is unclear. |
| Approach: | They compare the self-attention of several existing large language models in different sizes to assess the effect of scaling and instruction tuning on language perception. |
| Outcome: | The proposed models are closer to non-native speakers than native speakers in attention, suggesting a sub-optimal language perception of all models. |
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models (2025.acl-long)
Copied to clipboard
Zhisong Zhang, Yan Wang, Xinting Huang, Tianqing Fang, Hongming Zhang, Chenlong Deng, Shuaiyi Li, Dong Yu
| Challenge: | Large language models have demonstrated remarkable performance across a wide range of language tasks due to their remarkable ability in context modeling. |
| Approach: | They propose to use parallel context encoding to reduce attention entropy by incorporating attention sinks and selective mechanisms to reduce irregular attention . they also propose to incorporate attention sink mechanisms into the parallel encoded context to reduce the irregular attention. |
| Outcome: | The proposed methods lower irregular attention entropy and narrow performance gaps. |
Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models (2021.acl-long)
Copied to clipboard
| Challenge: | Recent work has shown that convolutions have been successful in natural language learning. |
| Approach: | They propose a convolutional approach to construct relative position embeddings in self-attention layers and propose 'compact attention' they propose multiple ways to integrate convolutions into Transformer self- attention. |
| Outcome: | The proposed composite attention improves performance on multiple downstream tasks, replacing absolute position embeddings, and is more expressive than convolutions in NLP. |