mlsanityData to 7 Oct 2026

Readers make targeted regressions to plausible errors in reanalysis of "noisy-channel garden-path" sentences

arXiv 2605.18563 ↗First posted 18 May 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

A key question in psycholinguistics is how inferences about the meaning of linguistic input unfold incrementally a comprehender's mind. In this work, we study reading dynamics for ``noisy-channel garden-path'' sentences, which temporarily appear well-formed but feature late-appearing violations of expectation that can be resolved not by inferring an alternative syntactic structure, but by inferring the presence of an error. We find evidence for targeted regressions -- eye movements towards regions that are promising loci of possible errors in light of later-arriving information, showing patterns consistent with the posterior inferences of a model of noisy-channel processing with reanalysis. We discuss the implications of these findings for theories of noisy-channel language comprehension and information-theoretic explanations of reading dynamics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 8 of its 53 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

8 of 53 references.

References · 8

  1. 2022Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?cited by 111
  2. 2023Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programscited by 79
  3. 2018Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!cited by 43
  4. 2017The Natural Stories Corpuscited by 40
  5. 2021Linguistic Dependencies and Statistical Dependencecited by 10
  6. 2024What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Lengthcited by 10
  7. 2024The Effect of Surprisal on Reading Times in Information Seeking and Repeated Readingcited by 8
  8. 2024An information-theoretic model of shallow and deep language comprehensioncited by 6

Built on by

Not cited yet.