The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The study examines whether bilingual language models can reflect the influence of a reader’s first language (L1) on second-language (L2) reading. By comparing bilingual models trained on an L1 that matches the readers’ backgrounds to monolingual English models and bilingual models trained on other L1s, the authors find that matching L1 improves predictions of L2 reading times, especially in late-stage eye-tracking measures and among intermediate-proficiency readers. The effect is modulated by the overlap between L1 and L2 scripts, indicating that bilingual models capture cross-linguistic influence in L2 reading behavior.
The study examines how reader proficiency influences the relationship between layer-wise surprisal from large language models (LLMs) and eye-tracking gaze measures. Using the MECO L2 corpus, researchers compared high- and low-proficiency readers on first-pass gaze duration (FPGD) and total gaze duration (TGD), finding that lower-proficiency readers exhibit deeper Predictive Depth for FPGD, while TGD shows deeper Predictive Depth across both groups. The results suggest that the distribution of predictive power across LLM layers relates to the timing and breadth of reading processes and varies with reader proficiency.
arXiv:2607. 08152v1 Announce Type: cross Abstract: On the recent EyeBench benchmark, predicting reading comprehension from eye movements exposes a stark gap: text-aware models using pretrained language models reach 56--63% AUROC, while gaze-only models operate at chance.
The study examines how reading times differ between human-written texts and rewrites generated by large language models (LLMs). Using a RoBERTa-RT model trained on eye-tracking data, the authors compare predicted reading times for 496 paired articles and find that LLM rewrites are shorter overall but have higher predicted reading times per word. These differences correlate with linguistic changes such as longer, less frequent words, greater lexical diversity, and higher contextual predictability.
The paper investigates how Vision‑Language Models (VLMs) often report high confidence even after self‑correcting or arriving at wrong answers, a phenomenon the authors attribute to the verbalized confidence being largely independent of the model’s reasoning trajectory. By analyzing content variation, token masking, and hesitation markers, the authors demonstrate that confidence does not adequately reflect the actual reasoning process and that calibration training can sometimes worsen this disconnect. To address this blind spot, they introduce the Trajectory‑Grounding Score (TGS) in two forms—TGS‑self and TGS‑pair—and propose TGS‑Bench, a suite of 10 benchmarks that reveal divergences between conventional calibration metrics and trajectory‑grounded confidence.
arXiv:2607.08152v2 Announce Type: replace-cross Abstract: Predicting comprehension from eye movements could support adaptive reading interfaces. We present LEXIC, a compact recurrent model that predi...