# Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention

arXiv: https://arxiv.org/abs/2104.12874 · HTML: https://mlsanity.com/paper/2104.12874/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 47 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Analyzing the Structure of Attention in a Transformer Language Model](https://mlsanity.com/paper/1906.04284/) (2019)
- [Open Sesame: Getting Inside BERT's Linguistic Knowledge](https://mlsanity.com/paper/1906.01698/) (2019)
- [On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behavior](https://mlsanity.com/paper/2006.01912/) (2020)
- [Attention in Natural Language Processing](https://mlsanity.com/paper/1902.02181/) (2019)
- [Syntactic Structure from Deep Learning](https://mlsanity.com/paper/2004.10827/) (2020)
- [What do RNN Language Models Learn about Filler-Gap Dependencies?](https://mlsanity.com/paper/1809.00042/) (2018)
- [ConvoKit: A Toolkit for the Analysis of Conversations](https://mlsanity.com/paper/2005.04246/) (2020)
- [RNNs as psycholinguistic subjects: Syntactic state and grammatical dependency](https://mlsanity.com/paper/1809.01329/) (2018)
- [What Syntactic Structures block Dependencies in RNN Language Models?](https://mlsanity.com/paper/1905.10431/) (2019)

## Built on by (most cited first, 27 of 27)

- [Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?](https://mlsanity.com/paper/2212.12131/) (2022)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing](https://mlsanity.com/paper/2310.16142/) (2023)
- [Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal](https://mlsanity.com/paper/2212.11185/) (2022)
- [Linear Recency Bias During Training Improves Transformers' Fit to Reading Times](https://mlsanity.com/paper/2409.11250/) (2024)
- [A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles](https://mlsanity.com/paper/2410.16139/) (2024)
- [Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?](https://mlsanity.com/paper/2310.17774/) (2023)
- [From Form(s) to Meaning: Probing the Semantic Depths of Language Models Using Multisense Consistency](https://mlsanity.com/paper/2404.12145/) (2024)
- [Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics](https://mlsanity.com/paper/2404.19178/) (2024)
- [Probing Syntax in Large Language Models: Successes and Remaining Challenges](https://mlsanity.com/paper/2508.03211/) (2025)
- [If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?](https://mlsanity.com/paper/2502.11469/) (2025)
- [What Makes Language Models Good-enough?](https://mlsanity.com/paper/2406.03666/) (2024)
- [N-gram-like Language Models Predict Naturalistic Reading Time Best](https://mlsanity.com/paper/2603.09872/) (2026)
- [Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects](https://mlsanity.com/paper/2603.16574/) (2026)
- [Plausibility Processing in Transformer Language Models: Focusing on the Role of Attention Heads in GPT](https://mlsanity.com/paper/2310.13824/) (2023)
- [Predicting Human Translation Difficulty with Neural Machine Translation](https://mlsanity.com/paper/2312.11852/) (2023)
- [Uniform Information Density and Syntactic Reduction: Revisiting textitthat-Mentioning in English Complement Clauses](https://mlsanity.com/paper/2509.05254/) (2025)
- [The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models](https://mlsanity.com/paper/2601.19926/) (2026)
- [Disaggregation Reveals Hidden Training Dynamics: The Case of Agreement Attraction](https://mlsanity.com/paper/2510.24934/) (2025)
- [Memory Retrieval in Transformers: Insights from The Encoding Specificity Principle](https://mlsanity.com/paper/2601.20282/) (2026)
- [Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity](https://mlsanity.com/paper/2604.20789/) (2026)
- [A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Models](https://mlsanity.com/paper/2604.26351/) (2026)
- [Quantifying the cross-linguistic effects of syncretism on agreement attraction](https://mlsanity.com/paper/2605.21403/) (2026)
- [When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs](https://mlsanity.com/paper/2606.21203/) (2026)
- [Timesteps of Mamba Align with Human Reading Times](https://mlsanity.com/paper/2606.29904/) (2026)
- [Beyond Static and Linear: What Attention Constraints Best Fit Human Reading Times?](https://mlsanity.com/paper/2608.23818/) (2026)
- [Do Syntax Heads Influence Model Behavior?](https://mlsanity.com/paper/2610.19231/) (2026)

## Abstract (arXiv)

We advance a novel explanation of similarity-based interference effects in subject-verb and reflexive pronoun agreement processing, grounded in surprisal values computed from a pretrained large-scale Transformer model, GPT-2. Specifically, we show that surprisal of the verb or reflexive pronoun predicts facilitatory interference effects in ungrammatical sentences, where a distractor noun that matches in number with the verb or pronoun leads to faster reading times, despite the distractor not participating in the agreement relation. We review the human empirical evidence for such effects, including recent meta-analyses and large-scale studies. We also show that attention patterns (indexed by entropy and other measures) in the Transformer show patterns of diffuse attention in the presence of similar distractors, consistent with cue-based retrieval models of parsing. But in contrast to these models, the attentional cues and memory representations are learned entirely from the simple self-supervised task of predicting the next word.