# An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal

arXiv: https://arxiv.org/abs/2604.18293 · HTML: https://mlsanity.com/paper/2604.18293/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 50 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behavior](https://mlsanity.com/paper/2006.01912/) (2020)
- [Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?](https://mlsanity.com/paper/2212.12131/) (2022)
- [Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora](https://mlsanity.com/paper/2504.08165/) (2025)
- [How to Compute the Probability of a Word](https://mlsanity.com/paper/2406.14561/) (2024)
- [Context Limitations Make Neural Language Models More Human-Like](https://mlsanity.com/paper/2205.11463/) (2022)
- [Syntactic Surprisal From Neural Models Predicts, But Underestimates, Human Processing Difficulty From Syntactic Ambiguities](https://mlsanity.com/paper/2210.12187/) (2022)
- [Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities](https://mlsanity.com/paper/2406.10851/) (2024)
- [On the Effect of Anticipation on Reading Times](https://mlsanity.com/paper/2211.14301/) (2022)
- [Reverse-Engineering the Reader](https://mlsanity.com/paper/2410.13086/) (2024)
- [Studies with impossible languages falsify LMs as models of human language](https://mlsanity.com/paper/2511.11389/) (2025)

## Built on by (most cited first, 1 of 1)

- [Surprisal Theory is Tautological (without Rational Grounding)](https://mlsanity.com/paper/2607.21574/) (2026)

## Abstract (arXiv)

Surprisal theory hypothesizes that the difficulty of human sentence processing increases linearly with surprisal, the negative log-probability of a word given its context. Computational psycholinguistics has tested this hypothesis using language models (LMs) as proxies for human prediction. While surprisal derived from recent neural LMs generally captures human processing difficulty on naturalistic corpora that predominantly consist of simple sentences, it severely underestimates processing difficulty on sentences that require syntactic disambiguation (garden-path effects). This leads to the claim that the processing difficulty of such sentences cannot be reduced to surprisal, although it remains possible that neural LMs simply differ from humans in next-word prediction. In this paper, we investigate whether it is truly impossible to construct a neural LM that can explain garden-path effects via surprisal. Specifically, instead of evaluating off-the-shelf neural LMs, we fine-tune these LMs on garden-path sentences so as to better align surprisal-based reading-time estimates with actual human reading times. Our results show that fine-tuned LMs do not overfit and successfully capture human reading slowdowns on held-out garden-path items; they even improve predictive power for human reading times on naturalistic corpora and preserve their general LM capabilities. These results provide an existence proof for a neural LM that can explain both garden-path effects and naturalistic reading times via surprisal, but also raise a theoretical question: what kind of evidence can truly falsify surprisal theory?