---
title: "Language Proficiency Assessment from Eye Movements in"
description: "This paper tests an alternative proposed by Berzak et al. (2018), which infers L2 proficiency from gaze behaviour during… 63 references."
authors: ["Shachar Frenkel", "Ido Falah", "Omer Shubi", "Yevgeni Berzak"]
year: 2026
venue: "arXiv:2608.30583"
source: "https://arxiv.org/abs/2608.30583"
doi: "10.48550/arxiv.2608.30583"
arxiv: "2608.30583"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/frenkel-2026-language-proficiency-assessment-eye-movements/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/frenkel-2026-language-proficiency-assessment-eye-movements/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/38/) / Language Proficiency Assessment from Eye Movements in Naturalistic Passage Reading

# Language Proficiency Assessment from Eye Movements in Naturalistic Passage Reading

**Authors:** Shachar Frenkel, Ido Falah, Omer Shubi and [Yevgeni Berzak](https://md.research.elamur.ai/free/en/authors/yevgeni-berzak/) · **Year:** 2026 · **Venue:** arXiv:2608.30583 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2608.30583) · [PDF](https://arxiv.org/pdf/2608.30583) · [DOI 10.48550/arxiv.2608.30583](https://doi.org/10.48550/arxiv.2608.30583) · [arXiv 2608.30583](https://arxiv.org/abs/2608.30583) · [OpenAlex](https://openalex.org/W7204944591)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Conventional English proficiency exams are costly, slow to build, and rely only on final answers to a small set of items. This paper tests an alternative proposed by Berzak et al. (2018), which infers L2 proficiency from gaze behaviour during ordinary reading. The original work used single sentences. Here the idea is moved to connected passages, drawing on 1,265 L2 readers from MECO L2 and OneStopL2, with L1 readers from OneStop as well. The authors use two scoring routes:
- **EyeScore**, a reference-free score measuring how closely a reader's gaze profile matches an average L1 reader.
- **Regression**, using Ridge, LightGBM and TabPFN-3 to predict scores on external tests.

Both routes work across datasets, proficiency measures, models, and an information-seeking reading mode. Two practical concerns are examined. EyeScore systematically favours readers whose native language is closer to English, and the authors propose a correction for this. On reliability, EyeScore is more internally consistent than standardized exams. Together, these findings make gaze-based assessment a more credible candidate for real use.

## Key points
- **EyeScore computation:**
  - Features are z-scaled using statistics from the L2 group.
  - The scaled vectors of L1 readers are averaged into a prototype.
  - Each L2 reader's score is the cosine similarity between their vector and that prototype.
- **Feature families:**
  - Averaged fixation measures (FF, GD, TF, GP, skip rate, regression probability).
  - The same measures broken down by Universal and PTB POS tags (S-Clusters).
  - Per-reader regression coefficients for word length, Wordfreq frequency and GPT-2 surprisal (WP-Coefs).
  - Word-to-word saccade counts and per-token GD/TF. These last two need all readers to see identical texts.
- **Baselines:** words per minute, which needs no eye tracker, and the training-set mean score.
- **Bias:** EyeScore is skewed toward readers whose L1 is closer to English. The proposed fix depends on estimated language distances from English and on an external reference test.
- **Reliability:** In the Any Text regime, EyeScore averages Cronbach's α 0.98 and split-half r 0.93. Split-half r is the mean over 20 random passage splits, computed on the 144 readers who read all 12 passages. For comparison:
  - Michigan test: α 0.91
  - IELTS (reading and listening average): α 0.91
  - TOEFL-iBT: 0.90

## Interesting ideas
- Turn a reference population into a single averaged prototype vector, normalized with the target group's statistics, and rate each item by cosine similarity to it; this yields a score with no labels needed.
- Instead of raw measurements, describe each subject by the coefficients of a small linear model that shows how strongly length, frequency and surprisal drive its behaviour; this captures sensitivity rather than level.
- Always compare against a cheap baseline that needs none of the expensive machinery (reading speed with no eye tracker), so the added value of the costly signal is measured honestly.
- Measure the stability of a score by splitting the test items into random halves many times and averaging the correlation, alongside Cronbach's α.
- Check whether a score is skewed by a nuisance property (here, how close the reader's L1 is to English), using an external reference to decide how much of the gap is unfair, and then correct for it.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): Build a feature profile (arc lengths, label mix, non-projectivity) from gold UD treebank trees, then rate each silver parse by its similarity to that profile to flag odd trees before training.
- **I2** (learn): Fit a per-model-version regression of parser error on sentence length, word frequency and surprisal, and track how those coefficients change as an explainable diagnostic.
- **I3** (answer): Report every reader's score next to a no-tree heuristic or majority baseline on school tests and fable QA, to show what the UD tree and frames actually contribute.
- **I4** (answer): Apply repeated split-half checks to school-course test sets to see whether accuracy differences between Mova versions are stable or just noise from a few items.
- **I5** (tree): Test whether parser quality depends on how close the input's register or origin is to the training treebanks, for example non-native or dialectal English, before trusting the scores as a general measure.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,649 works · [💭 Developmental and Educational Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/developmental-and-educational-psychology/) · 523 works · [🖱️ Human-Computer Interaction](https://md.research.elamur.ai/free/en/shelves/computer-science/human-computer-interaction/) · 160 works

## Cite

Cite as: Shachar Frenkel, Ido Falah, Omer Shubi and Yevgeni Berzak. 2026. Language Proficiency Assessment from Eye Movements in Naturalistic Passage Reading. arXiv:2608.30583.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{frenkel2026language,
  title = {{Language Proficiency Assessment from Eye Movements in Naturalistic Passage Reading}},
  author = {Shachar Frenkel, Ido Falah, Omer Shubi and Yevgeni Berzak},
  year = {2026},
  doi = {10.48550/arxiv.2608.30583},
  eprint = {2608.30583},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2608.30583}
}
```

- [← previous Language Proficiency as a Recoverable Dimension in Multilingual LLM Embeddings](https://md.research.elamur.ai/free/en/papers/wilkens-2026-language-proficiency-as-recoverable-dimension/)
- [next → Language Technology Initiative: Framework for Teaching NLP and Computational Linguistics at the Universities in Latvia](https://md.research.elamur.ai/free/en/papers/skadina-2026-language-technology-initiative-framework-teaching/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/38/)

## References

63 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Seoyoung Ahn, Conor Kelton, Aruna Balasubramanian, and Greg Zelinsky. 2020. Towards predicting reading comprehension from gaze behavior. In Symposium on Eye Tracking Research and Applications, pages 1–5. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Seoyoung+Ahn%2C+Conor+Kelton%2C+Aruna+Balasubramanian%2C+and+Greg+Zelinsky%2E+2020%2E+Towards+predicting+reading+comprehension+from+gaze+behavior%2E+In+Symposium+on+Eye+Tracking+Research+and+Applications%2C+pages+1)
2. Sally Andrews and Jolyn Hersch. 2010. Lexical precision in skilled readers: Individual differences in masked neighbor priming. Journal of Experimental Psychology: General, 139(2):299. [find](https://scholar.google.com/scholar?q=Sally+Andrews+and+Jolyn+Hersch%2E+2010%2E+Lexical+precision+in+skilled+readers%3A+Individual+differences+in+masked+neighbor+priming%2E+Journal+of+Experimental+Psychology%3A+General%2C+139%282%29%3A299%2E)
3. David Beglar. 2010. A Rasch-based validation of the Vocabulary Size Test. Language testing, 27(1):101– 118. [find](https://scholar.google.com/scholar?q=David+Beglar%2E+2010%2E+A+Rasch%2Dbased+validation+of+the+Vocabulary+Size+Test%2E+Language+testing%2C+27%281%29%3A101%E2%80%93+118%2E)
4. Yevgeni Berzak, Boris Katz, and Roger Levy. 2018. Assessing language proficiency from eye movements in reading. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1986–1996, New Orleans, Louisiana. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yevgeni+Berzak%2C+Boris+Katz%2C+and+Roger+Levy%2E+2018%2E+Assessing+language+proficiency+from+eye+movements+in+reading%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chapter+of+the+Association+f)
5. Yevgeni Berzak and Roger Levy. 2023. Eye movement traces of linguistic knowledge in native and non-native reading. Open Mind, 7:179–196. [find](https://scholar.google.com/scholar?q=Yevgeni+Berzak+and+Roger+Levy%2E+2023%2E+Eye+movement+traces+of+linguistic+knowledge+in+native+and+non%2Dnative+reading%2E+Open+Mind%2C+7%3A179%E2%80%93196%2E)
6. Yevgeni Berzak, Jonathan Malmaud, Omer Shubi, Yoav Meiri, Ella Lion, and Roger Levy. 2025. OneStop: A 360-participant English eye tracking dataset with different reading regimes. Scientific Data. [find](https://scholar.google.com/scholar?q=Yevgeni+Berzak%2C+Jonathan+Malmaud%2C+Omer+Shubi%2C+Yoav+Meiri%2C+Ella+Lion%2C+and+Roger+Levy%2E+2025%2E+OneStop%3A+A+360%2Dparticipant+English+eye+tracking+dataset+with+different+reading+regimes%2E+Scientific+Data%2E)
7. Yevgeni Berzak, Chie Nakamura, Suzanne Flynn, and Boris Katz. 2017. Predicting native language from gaze. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 541–551. [find](https://scholar.google.com/scholar?q=Yevgeni+Berzak%2C+Chie+Nakamura%2C+Suzanne+Flynn%2C+and+Boris+Katz%2E+2017%2E+Predicting+native+language+from+gaze%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Vo)
8. Yevgeni Berzak, Chie Nakamura, Amelia Smith, Emily Weng, Boris Katz, Suzanne Flynn, and Roger Levy. 2022. CELER: A 365-participant corpus of eye movements in L1 and L2 English reading. Open Mind, 6:41–50. [find](https://scholar.google.com/scholar?q=Yevgeni+Berzak%2C+Chie+Nakamura%2C+Amelia+Smith%2C+Emily+Weng%2C+Boris+Katz%2C+Suzanne+Flynn%2C+and+Roger+Levy%2E+2022%2E+CELER%3A+A+365%2Dparticipant+corpus+of+eye+movements+in+L1+and+L2+English+reading%2E+Open+Mind%2C+6%3A41)
9. Eugene Charniak, Don Blaheta, Niyu Ge, Keith Hall, John Hale, and Mark Johnson. 2000. BLLIP 1987-89 WSJ corpus release 1. Linguistic Data Consortium, Philadelphia, 36. [find](https://scholar.google.com/scholar?q=Eugene+Charniak%2C+Don+Blaheta%2C+Niyu+Ge%2C+Keith+Hall%2C+John+Hale%2C+and+Mark+Johnson%2E+2000%2E+BLLIP+1987%2D89+WSJ+corpus+release+1%2E+Linguistic+Data+Consortium%2C+Philadelphia%2C+36%2E)
10. Ping-Lin Chuang and Xun Yan. 2025. Language assessment in the era of generative artificial intelligence: Opportunities, challenges, and future directions. System, 134:103846. [find](https://scholar.google.com/scholar?q=Ping%2DLin+Chuang+and+Xun+Yan%2E+2025%2E+Language+assessment+in+the+era+of+generative+artificial+intelligence%3A+Opportunities%2C+challenges%2C+and+future+directions%2E+System%2C+134%3A103846%2E)
11. Harald Clahsen and Claudia Felser. 2006. Grammatical processing in language learners. Applied Psycholinguistics, 27(1):3–42. [find](https://scholar.google.com/scholar?q=Harald+Clahsen+and+Claudia+Felser%2E+2006%2E+Grammatical+processing+in+language+learners%2E+Applied+Psycholinguistics%2C+27%281%29%3A3%E2%80%9342%2E)
12. Chris Collins and Richard Kayne. 2009. Syntactic structures of the world’s languages (SSWL). [find](https://scholar.google.com/scholar?q=Chris+Collins+and+Richard+Kayne%2E+2009%2E+Syntactic+structures+of+the+world%E2%80%99s+languages+%28SSWL%29%2E)
13. Uschi Cop, Denis Drieghe, and Wouter Duyck. 2015a. Eye movement patterns in natural reading: A comparison of monolingual and bilingual reading of a novel. PloS one, 10(8):e0134008. [find](https://scholar.google.com/scholar?q=Uschi+Cop%2C+Denis+Drieghe%2C+and+Wouter+Duyck%2E+2015a%2E+Eye+movement+patterns+in+natural+reading%3A+A+comparison+of+monolingual+and+bilingual+reading+of+a+novel%2E+PloS+one%2C+10%288%29%3Ae0134008%2E)
14. Uschi Cop, Emmanuel Keuleers, Denis Drieghe, and Wouter Duyck. 2015b. Frequency effects in monolingual and bilingual natural reading. Psychonomic bulletin & review, 22(5):1216–1234. [find](https://scholar.google.com/scholar?q=Uschi+Cop%2C+Emmanuel+Keuleers%2C+Denis+Drieghe%2C+and+Wouter+Duyck%2E+2015b%2E+Frequency+effects+in+monolingual+and+bilingual+natural+reading%2E+Psychonomic+bulletin+%26+review%2C+22%285%29%3A1216%E2%80%931234%2E)
15. Leana Copeland, Tom Gedeon, and Sumudu Mendis. 2014. Predicting reading comprehension scores from eye movements using artificial neural networks and fuzzy output error. Artificial Intelligence Research, 3(3):35–48. [find](https://scholar.google.com/scholar?q=Leana+Copeland%2C+Tom+Gedeon%2C+and+Sumudu+Mendis%2E+2014%2E+Predicting+reading+comprehension+scores+from+eye+movements+using+artificial+neural+networks+and+fuzzy+output+error%2E+Artificial+Intelligence+Researc)
16. Lee J Cronbach. 1951. Coefficient alpha and the internal structure of tests. Psychometrika, 16(3):297–334. [find](https://scholar.google.com/scholar?q=Lee+J+Cronbach%2E+1951%2E+Coefficient+alpha+and+the+internal+structure+of+tests%2E+Psychometrika%2C+16%283%29%3A297%E2%80%93334%2E)
17. Lee J Cronbach, Peter Schönemann, and Douglas McKie. 1965. Alpha coefficients for stratified-parallel tests. Educational and Psychological Measurement, 25(2):291–312. [find](https://scholar.google.com/scholar?q=Lee+J+Cronbach%2C+Peter+Sch%C3%B6nemann%2C+and+Douglas+McKie%2E+1965%2E+Alpha+coefficients+for+stratified%2Dparallel+tests%2E+Educational+and+Psychological+Measurement%2C+25%282%29%3A291%E2%80%93312%2E)
18. Vera Demberg and Frank Keller. 2008. Data from eye-tracking corpora as evidence for theories of syntactic processing complexity. Cognition, 109(2):193–210. [↗](https://doi.org/10.1016/j.cognition.2008.07.008)
19. Matthew Dryer and Martin Haspelmath. 2022. The world atlas of language structures online. [find](https://scholar.google.com/scholar?q=Matthew+Dryer+and+Martin+Haspelmath%2E+2022%2E+The+world+atlas+of+language+structures+online%2E)
20. Education First. 2025. EF EPI: EF English proficiency index: A ranking of 123 countries and regions by English skills. Accessed 29 August 2026. [find](https://scholar.google.com/scholar?q=Education+First%2E+2025%2E+EF+EPI%3A+EF+English+proficiency+index%3A+A+ranking+of+123+countries+and+regions+by+English+skills%2E+Accessed+29+August+2026%2E)
21. Ralf Engbert, Antje Nuthmann, Eike M Richter, and Reinhold Kliegl. 2005. SWIFT: a dynamical model of saccade generation during reading. Psychological review, 112(4):777. [find](https://scholar.google.com/scholar?q=Ralf+Engbert%2C+Antje+Nuthmann%2C+Eike+M+Richter%2C+and+Reinhold+Kliegl%2E+2005%2E+SWIFT%3A+a+dynamical+model+of+saccade+generation+during+reading%2E+Psychological+review%2C+112%284%29%3A777%2E)
22. Léo Grinsztajn, Klemens Flöge, Oscar Key, Felix Birkel, Philipp Jund, Brendan Roof, Mihir Manium, Shi Bin Hoo, Magnus Bühler, Anurag Garg, Dominik Safaric, Jake Robertson, Benjamin Jäger, Simone Alessi, Adrian Hayler, Vladyslav Moroshan, Lennart Purucker, Philipp Singer, Alan Arazi, and 22 others. 2026. TabPFN-3: Technical report. Preprint, arXiv:2605.13986. [↗](https://arxiv.org/abs/2605.13986)
23. Patrick Haller, Andreas Säuberli, Sarah Kiener, Jinger Pan, Ming Yan, and Lena Jäger. 2022. Eye-tracking based classification of Mandarin Chinese readers with and without dyslexia using neural sequence models. In Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022), pages 111–118. [find](https://scholar.google.com/scholar?q=Patrick+Haller%2C+Andreas+S%C3%A4uberli%2C+Sarah+Kiener%2C+Jinger+Pan%2C+Ming+Yan%2C+and+Lena+J%C3%A4ger%2E+2022%2E+Eye%2Dtracking+based+classification+of+Mandarin+Chinese+readers+with+and+without+dyslexia+using+neural+sequenc)
24. Leo M Harvill. 1991. Standard error of measurement: an NCME instructional module on. Educational Measurement: issues and practice, 10(2):33–41. [find](https://scholar.google.com/scholar?q=Leo+M+Harvill%2E+1991%2E+Standard+error+of+measurement%3A+an+NCME+instructional+module+on%2E+Educational+Measurement%3A+issues+and+practice%2C+10%282%29%3A33%E2%80%9341%2E)
25. Steph Holloway. 2013. ScriptSource – Writing systems, computers and people. SIL International. [find](https://scholar.google.com/scholar?q=Steph+Holloway%2E+2013%2E+ScriptSource+%E2%80%93+Writing+systems%2C+computers+and+people%2E+SIL+International%2E)
26. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. spaCy: Industrial-strength Natural Language Processing in Python. [find](https://scholar.google.com/scholar?q=Matthew+Honnibal%2C+Ines+Montani%2C+Sofie+Van+Lan%2Ddeghem%2C+and+Adriane+Boyd%2E+2020%2E+spaCy%3A+Industrial%2Dstrength+Natural+Language+Processing+in+Python%2E)
27. IELTS. 2026. Test statistics. Accessed August 18th, 2026. [find](https://scholar.google.com/scholar?q=IELTS%2E+2026%2E+Test+statistics%2E+Accessed+August+18th%2C+2026%2E)
28. Naoki Ikeda, Tony Clark, Spiros Papageorgiou, Lixiong Gu, Renka Ohta, Andrew Blackhurst, and Emma Bruce. 2025. Aligning scores of language proficiency tests: A score concordance study between IELTS Academic and TOEFL iBT®. ETS Research Report Series, 2025(1):1–28. [find](https://scholar.google.com/scholar?q=Naoki+Ikeda%2C+Tony+Clark%2C+Spiros+Papageorgiou%2C+Lixiong+Gu%2C+Renka+Ohta%2C+Andrew+Blackhurst%2C+and+Emma+Bruce%2E+2025%2E+Aligning+scores+of+language+proficiency+tests%3A+A+score+concordance+study+between+IELTS+Ac)
29. Lena A Jäger, Silvia Makowski, Paul Prasse, Sascha Liehr, Maximilian Seidler, and Tobias Scheffer. 2019. Deep eyedentification: Biometric identification using micro-movements of the eye. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 299–314. Springer. [find](https://scholar.google.com/scholar?q=Lena+A+J%C3%A4ger%2C+Silvia+Makowski%2C+Paul+Prasse%2C+Sascha+Liehr%2C+Maximilian+Seidler%2C+and+Tobias+Scheffer%2E+2019%2E+Deep+eyedentification%3A+Biometric+identification+using+micro%2Dmovements+of+the+eye%2E+In+Joint+Euro)
30. Scott Jarvis and Aneta Pavlenko. 2008. Crosslinguistic influence in language and cognition. Routledge. [find](https://scholar.google.com/scholar?q=Scott+Jarvis+and+Aneta+Pavlenko%2E+2008%2E+Crosslinguistic+influence+in+language+and+cognition%2E+Routledge%2E)
31. Eun Hee Jeon and Junko Yamashita. 2014. L2 reading comprehension and its correlates: A meta-analysis. Language learning, 64(1):160–212. [find](https://scholar.google.com/scholar?q=Eun+Hee+Jeon+and+Junko+Yamashita%2E+2014%2E+L2+reading+comprehension+and+its+correlates%3A+A+meta%2Danalysis%2E+Language+learning%2C+64%281%29%3A160%E2%80%93212%2E)
32. Marcel A Just and Patricia A Carpenter. 1980. A theory of reading: from eye fixations to comprehension. Psychological review, 87(4):329. [find](https://scholar.google.com/scholar?q=Marcel+A+Just+and+Patricia+A+Carpenter%2E+1980%2E+A+theory+of+reading%3A+from+eye+fixations+to+comprehension%2E+Psychological+review%2C+87%284%29%3A329%2E)
33. Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Guolin+Ke%2C+Qi+Meng%2C+Thomas+Finley%2C+Taifeng+Wang%2C+Wei+Chen%2C+Weidong+Ma%2C+Qiwei+Ye%2C+and+Tie%2DYan+Liu%2E+2017%2E+LightGBM%3A+A+highly+efficient+gradient+boosting+decision+tree%2E+In+Advances+in+Neural+Information+)
34. Aditya Khan, Mason Shipton, David Anugraha, Kaiyao Duan, Phuong H. Hoang, Eric Khiu, A. Seza Doğruöz, and En-Shiun Annie Lee. 2025. [URIEL+: Enhancing linguistic inclusion and usability in a typological and multilingual knowledge base](https://md.research.elamur.ai/free/en/papers/khan-2025-uriel-enhancing-linguistic-inclusion-usability/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 6937–6952. Association for Computational Linguistics.
35. Reinhold Kliegl, Ellen Grabner, Martin Rolfs, and Ralf Engbert. 2004. Length, frequency, and predictability effects of words on eye movements in reading. European journal of cognitive psychology, 16(1-2):262– 284. [find](https://scholar.google.com/scholar?q=Reinhold+Kliegl%2C+Ellen+Grabner%2C+Martin+Rolfs%2C+and+Ralf+Engbert%2E+2004%2E+Length%2C+frequency%2C+and+predictability+effects+of+words+on+eye+movements+in+reading%2E+European+journal+of+cognitive+psychology%2C+16%281)
36. Michael J Kolen, Lingjia Zeng, and Bradley A Hanson. 1996. Conditional standard errors of measurement for scale scores using IRT. Journal of Educational Measurement, 33(2):129–140. [find](https://scholar.google.com/scholar?q=Michael+J+Kolen%2C+Lingjia+Zeng%2C+and+Bradley+A+Hanson%2E+1996%2E+Conditional+standard+errors+of+measurement+for+scale+scores+using+IRT%2E+Journal+of+Educational+Measurement%2C+33%282%29%3A129%E2%80%93140%2E)
37. Victor Kuperman, Sascha Schroeder, Cengiz Acartürk, Niket Agrawal, Dominick M Alexandre, Lena S Bolliger, Jan Brasser, César Campos-Rojas, Denis Drieghe, Dušica Filipović Ðurd̄ević, and 1 others. 2025. New data on text reading in English as a second language: The wave 2 expansion of the multilingual eye-movement corpus (MECO). Studies in Second Language Acquisition, 47(2):677–695. [find](https://scholar.google.com/scholar?q=Victor+Kuperman%2C+Sascha+Schroeder%2C+Cengiz+Acart%C3%BCrk%2C+Niket+Agrawal%2C+Dominick+M+Alexandre%2C+Lena+S+Bolliger%2C+Jan+Brasser%2C+C%C3%A9sar+Campos%2DRojas%2C+Denis+Drieghe%2C+Du%C5%A1ica+Filipovic%CC%81+%C3%90urd%CC%84evic%CC%81%2C+and+1+others%2E+20)
38. Victor Kuperman, Noam Siegelman, Sascha Schroeder, Cengiz Acartürk, Svetlana Alexeeva, Simona Amenta, Raymond Bertram, Rolando Bonandrini, Marc Brysbaert, Daria Chernova, and 1 others. 2023. Text reading in English as a second language: Evidence from the multilingual eye-movements corpus. Studies in second language acquisition, 45(1):3–37. [find](https://scholar.google.com/scholar?q=Victor+Kuperman%2C+Noam+Siegelman%2C+Sascha+Schroeder%2C+Cengiz+Acart%C3%BCrk%2C+Svetlana+Alexeeva%2C+Simona+Amenta%2C+Raymond+Bertram%2C+Rolando+Bonandrini%2C+Marc+Brysbaert%2C+Daria+Chernova%2C+and+1+others%2E+2023%2E+Text+read)
39. Anna Laurinavichyute, Anastasiya Lopukhina, and David Robert Reich. 2025. Automatic detection of dyslexia based on eye movements during reading in Russian. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 59–66. [find](https://scholar.google.com/scholar?q=Anna+Laurinavichyute%2C+Anastasiya+Lopukhina%2C+and+David+Robert+Reich%2E+2025%2E+Automatic+detection+of+dyslexia+based+on+eye+movements+during+reading+in+Russian%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of)
40. Kristin Lemhöfer and Mirjam Broersma. 2012. Introducing LexTALE: A quick and valid lexical test for advanced learners of English. Behavior research methods, 44(2):325–343. [find](https://scholar.google.com/scholar?q=Kristin+Lemh%C3%B6fer+and+Mirjam+Broersma%2E+2012%2E+Introducing+LexTALE%3A+A+quick+and+valid+lexical+test+for+advanced+learners+of+English%2E+Behavior+research+methods%2C+44%282%29%3A325%E2%80%93343%2E)
41. M. Paul Lewis, Gary F. Simons, and Charles D. Fennig. 2015. Ethnologue: Languages of the world. [find](https://scholar.google.com/scholar?q=M%2E+Paul+Lewis%2C+Gary+F%2E+Simons%2C+and+Charles+D%2E+Fennig%2E+2015%2E+Ethnologue%3A+Languages+of+the+world%2E)
42. Venessa Manna, Shuhong Li, Spiros Papageorgiou, and Lixiong Gu. 2025. TOEFL iBT® technical manual. ETS Research Report Series, 2025(1). [find](https://scholar.google.com/scholar?q=Venessa+Manna%2C+Shuhong+Li%2C+Spiros+Papageorgiou%2C+and+Lixiong+Gu%2E+2025%2E+TOEFL+iBT%C2%AE+technical+manual%2E+ETS+Research+Report+Series%2C+2025%281%29%2E)
43. Yoav Meiri, Omer Shubi, Cfir Avraham Hadar, Ariel Kreisberg Nitzav, and Yevgeni Berzak. 2025. Déjà vu? Decoding repeated reading from eye movements. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 19460–19482. [find](https://scholar.google.com/scholar?q=Yoav+Meiri%2C+Omer+Shubi%2C+Cfir+Avraham+Hadar%2C+Ariel+Kreisberg+Nitzav%2C+and+Yevgeni+Berzak%2E+2025%2E+D%C3%A9j%C3%A0+vu%3F+Decoding+repeated+reading+from+eye+movements%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+As)
44. Yoav Meiri, Omer Shubi, Keren Gruteke Klein, David R. Reich, and Yevgeni Berzak. 2026. lacclab/psycholing-metrics: v1.1.9. Zenodo. https://doi.org/10.5281/zenodo.20376826. [↗](https://doi.org/10.5281/zenodo.20376826)
45. Diane C. Mézière, Lili Yu, Erik D. Reichle, Titus von der Malsburg, and Genevieve McArthur. 2023. Using eye-tracking measures to predict reading comprehension. Reading Research Quarterly, 58(3):425–449. [find](https://scholar.google.com/scholar?q=Diane+C%2E+M%C3%A9zi%C3%A8re%2C+Lili+Yu%2C+Erik+D%2E+Reichle%2C+Titus+von+der+Malsburg%2C+and+Genevieve+McArthur%2E+2023%2E+Using+eye%2Dtracking+measures+to+predict+reading+comprehension%2E+Reading+Research+Quarterly%2C+58%283%29%3A425%E2%80%9344)
46. Terence Odlin. 1989. Language transfer. Cambridge, UK: Cambridge. [find](https://scholar.google.com/scholar?q=Terence+Odlin%2E+1989%2E+Language+transfer%2E+Cambridge%2C+UK%3A+Cambridge%2E)
47. Slav Petrov, Dipanjan Das, and Ryan McDonald. 2012. [A universal part-of-speech tagset](https://md.research.elamur.ai/free/en/papers/petrov-2012-universal-part-speech-tagset/). In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2089– 2096, Istanbul, Turkey. European Language Resources Association (ELRA).
48. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2E)
49. Keith Rayner, Jane Ashby, Alexander Pollatsek, and Erik D Reichle. 2004. The effects of frequency and predictability on eye fixations in reading: implications for the E-Z Reader model. Journal of Experimental Psychology: Human Perception and Performance, 30(4):720. [find](https://scholar.google.com/scholar?q=Keith+Rayner%2C+Jane+Ashby%2C+Alexander+Pollatsek%2C+and+Erik+D+Reichle%2E+2004%2E+The+effects+of+frequency+and+predictability+on+eye+fixations+in+reading%3A+implications+for+the+E%2DZ+Reader+model%2E+Journal+of+Expe)
50. Keith Rayner, Alexander Pollatsek, Jane Ashby, and Charles Clifton Jr. 2012. Psychology of reading. Psychology Press. [find](https://scholar.google.com/scholar?q=Keith+Rayner%2C+Alexander+Pollatsek%2C+Jane+Ashby%2C+and+Charles+Clifton+Jr%2E+2012%2E+Psychology+of+reading%2E+Psychology+Press%2E)
51. David Robert Reich, Paul Prasse, Chiara Tschirner, Patrick Haller, Frank Goldhammer, and Lena A Jäger. 2022. Inferring native and non-native human reading comprehension and subjective text difficulty from scanpaths in reading. In 2022 Symposium on eye tracking research and applications, pages 1–8. [find](https://scholar.google.com/scholar?q=David+Robert+Reich%2C+Paul+Prasse%2C+Chiara+Tschirner%2C+Patrick+Haller%2C+Frank+Goldhammer%2C+and+Lena+A+J%C3%A4ger%2E+2022%2E+Inferring+native+and+non%2Dnative+human+reading+comprehension+and+subjective+text+difficulty+)
52. Erik D Reichle, Alexander Pollatsek, Donald L Fisher, and Keith Rayner. 1998. Toward a model of eye movement control in reading. Psychological review, 105(1):125. [find](https://scholar.google.com/scholar?q=Erik+D+Reichle%2C+Alexander+Pollatsek%2C+Donald+L+Fisher%2C+and+Keith+Rayner%2E+1998%2E+Toward+a+model+of+eye+movement+control+in+reading%2E+Psychological+review%2C+105%281%29%3A125%2E)
53. Luz Rello and Miguel Ballesteros. 2015. Detecting readers with dyslexia using machine learning with eye tracking measures. In Proceedings of the 12th international web for all conference, pages 1–8. [find](https://scholar.google.com/scholar?q=Luz+Rello+and+Miguel+Ballesteros%2E+2015%2E+Detecting+readers+with+dyslexia+using+machine+learning+with+eye+tracking+measures%2E+In+Proceedings+of+the+12th+international+web+for+all+conference%2C+pages+1%E2%80%938%2E)
54. Beatrice Santorini. 1990. [Part-of-speech tagging guidelines for the Penn Treebank project (3rd revision, 2nd printing)](https://md.research.elamur.ai/free/en/papers/santorini-1990-part-of-speech-tagging-guidelines-penn-treebank/). Ms., Department of Linguistics, UPenn. Philadelphia, PA.
55. Elizabeth R Schotter and Brian Dillon. 2025. A beginner’s guide to eye tracking for psycholinguistic studies of reading. Behavior research methods, 57(2):68. [find](https://scholar.google.com/scholar?q=Elizabeth+R+Schotter+and+Brian+Dillon%2E+2025%2E+A+beginner%E2%80%99s+guide+to+eye+tracking+for+psycholinguistic+studies+of+reading%2E+Behavior+research+methods%2C+57%282%29%3A68%2E)
56. Omer Shubi, Cfir Avraham Hadar, and Yevgeni Berzak. 2025a. Decoding reading goals from eye movements. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5616–5637. [find](https://scholar.google.com/scholar?q=Omer+Shubi%2C+Cfir+Avraham+Hadar%2C+and+Yevgeni+Berzak%2E+2025a%2E+Decoding+reading+goals+from+eye+movements%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume)
57. Omer Shubi, Yoav Meiri, Cfir Avraham Hadar, and Yevgeni Berzak. 2024. Fine-grained prediction of reading comprehension from eye movements. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3372–3391. [find](https://scholar.google.com/scholar?q=Omer+Shubi%2C+Yoav+Meiri%2C+Cfir+Avraham+Hadar%2C+and+Yevgeni+Berzak%2E+2024%2E+Fine%2Dgrained+prediction+of+reading+comprehension+from+eye+movements%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in)
58. Omer Shubi, David Robert Reich, Keren Gruteke Klein, Yuval Angel, Paul Prasse, Lena Ann Jäger, and Yevgeni Berzak. 2025b. EyeBench: Predictive modeling from eye movements in reading. In The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track. [find](https://scholar.google.com/scholar?q=Omer+Shubi%2C+David+Robert+Reich%2C+Keren+Gruteke+Klein%2C+Yuval+Angel%2C+Paul+Prasse%2C+Lena+Ann+J%C3%A4ger%2C+and+Yevgeni+Berzak%2E+2025b%2E+EyeBench%3A+Predictive+modeling+from+eye+movements+in+reading%2E+In+The+Thirty%2Dnin)
59. Lina Skerath, Paulina Toborek, Anita Zielińska, Maria Barrett, and Rob Van Der Goot. 2023. Native language prediction from gaze: a reproducibility study. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop), pages 152–159. [find](https://scholar.google.com/scholar?q=Lina+Skerath%2C+Paulina+Toborek%2C+Anita+Zielin%CC%81ska%2C+Maria+Barrett%2C+and+Rob+Van+Der+Goot%2E+2023%2E+Native+language+prediction+from+gaze%3A+a+reproducibility+study%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+)
60. Robyn Speer, Joshua Chin, Andrew Lin, Sara Jewett, and Lance Nathan. 2018. LuminosoInsight/wordfreq: v2.2. [find](https://scholar.google.com/scholar?q=Robyn+Speer%2C+Joshua+Chin%2C+Andrew+Lin%2C+Sara+Jewett%2C+and+Lance+Nathan%2E+2018%2E+LuminosoInsight%2Fwordfreq%3A+v2%2E2%2E)
61. Joseph K Torgesen, Carol Alexander Rashotte, and Richard K Wagner. 1999. TOWRE: Test of word reading efficiency. Pro-ed Austin, TX. [find](https://scholar.google.com/scholar?q=Joseph+K+Torgesen%2C+Carol+Alexander+Rashotte%2C+and+Richard+K+Wagner%2E+1999%2E+TOWRE%3A+Test+of+word+reading+efficiency%2E+Pro%2Ded+Austin%2C+TX%2E)
62. Veronica Whitford and Debra Titone. 2012. Second-language experience modulates first-and second-language word frequency effects: Evidence from eye movement measures of natural paragraph reading. Psychonomic bulletin & review, 19(1):73–80. [find](https://scholar.google.com/scholar?q=Veronica+Whitford+and+Debra+Titone%2E+2012%2E+Second%2Dlanguage+experience+modulates+first%2Dand+second%2Dlanguage+word+frequency+effects%3A+Evidence+from+eye+movement+measures+of+natural+paragraph+reading%2E+Psych)
63. Veronica Whitford and Debra Titone. 2017. The effects of word frequency and word predictability during first-and second-language paragraph reading in bilingual older and younger adults. Psychology and aging, 32(2):158. [find](https://scholar.google.com/scholar?q=Veronica+Whitford+and+Debra+Titone%2E+2017%2E+The+effects+of+word+frequency+and+word+predictability+during+first%2Dand+second%2Dlanguage+paragraph+reading+in+bilingual+older+and+younger+adults%2E+Psychology+and)

*Updated 2 November 2026*