# Reverse-Engineering the Reader

arXiv: https://arxiv.org/abs/2410.13086 · HTML: https://mlsanity.com/paper/2410.13086/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 64 references that are in the map.
- First posted on arXiv 16 Oct 2024.

## Builds on (most cited first, 30 of 30)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [The LAMBADA dataset: Word prediction requiring a broad discourse context](https://mlsanity.com/paper/1606.06031/) (2016)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)](https://mlsanity.com/paper/1905.11833/) (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)
- [Testing the Predictions of Surprisal Theory in 11 Languages](https://mlsanity.com/paper/2307.03667/) (2023)
- [Revisiting the Uniform Information Density Hypothesis](https://mlsanity.com/paper/2109.11635/) (2021)
- [ZuCo 2.0: A Dataset of Physiological Recordings During Natural Reading and Annotation](https://mlsanity.com/paper/1912.00903/) (2019)
- [Lower Perplexity is Not Always Human-Like](https://mlsanity.com/paper/2106.01229/) (2021)
- [Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens](https://mlsanity.com/paper/2304.11389/) (2023)
- [How to Compute the Probability of a Word](https://mlsanity.com/paper/2406.14561/) (2024)
- [Preference Tuning For Toxicity Mitigation Generalizes Across Languages](https://mlsanity.com/paper/2406.16235/) (2024)
- [Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities](https://mlsanity.com/paper/2406.10851/) (2024)
- [Multilingual Language Models Predict Human Reading Behavior](https://mlsanity.com/paper/2104.05433/) (2021)
- [Deep Eyedentification: Biometric Identification using Micro-Movements of the Eye](https://mlsanity.com/paper/1906.11889/) (2019)
- [On the Role of Context in Reading Time Prediction](https://mlsanity.com/paper/2409.08160/) (2024)
- [On the Effect of Anticipation on Reading Times](https://mlsanity.com/paper/2211.14301/) (2022)
- [A Cross-Linguistic Pressure for Uniform Information Density in Word Order](https://mlsanity.com/paper/2306.03734/) (2023)
- [Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures](https://mlsanity.com/paper/2311.04547/) (2023)
- [EMTeC: A Corpus of Eye Movements on Machine-Generated Texts](https://mlsanity.com/paper/2408.04289/) (2024)

## Built on by (most cited first, 2 of 2)

- [An Existence Proof for Neural Language Models That Can Explain Garden-Path Effects via Surprisal](https://mlsanity.com/paper/2604.18293/) (2026)
- [Revisiting the Estimation of Unigram Surprisal in Computational Psycholinguistics](https://mlsanity.com/paper/2610.18414/) (2026)

## Abstract (arXiv)

Numerous previous studies have sought to determine to what extent language models, pretrained on natural language text, can serve as useful models of human cognition. In this paper, we are interested in the opposite question: whether we can directly optimize a language model to be a useful cognitive model by aligning it to human psychometric data. To achieve this, we introduce a novel alignment technique in which we fine-tune a language model to implicitly optimize the parameters of a linear regressor that directly predicts humans' reading times of in-context linguistic units, e.g., phonemes, morphemes, or words, using surprisal estimates derived from the language model. Using words as a test case, we evaluate our technique across multiple model sizes and datasets and find that it improves language models' psychometric predictive power. However, we find an inverse relationship between psychometric power and a model's performance on downstream NLP tasks as well as its perplexity on held-out test data. While this latter trend has been observed before (Oh et al., 2022; Shain et al., 2024), we are the first to induce it by manipulating a model's alignment to psychometric data.