analiza aiqbench
This article focuses on LEXIC, a lightweight machine learning model designed to predict reading comprehension from eye-tracking data without relying on large language models. By operating efficiently on-device with minimal parameters and CPU usage, the research targets adaptive human-computer interaction interfaces rather than general AI capabilities or quantum applications. The primary contribution lies in advancing efficient ML architectures for specific HCI tasks, making it a relevant development within machine learning optimization.
LEXIC: Lightweight On-Device Decoding of Reading Comprehension from Eye Movements
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 predicts response correctness from fixation sequences, word frequency, and character length. It has 41.6K parameters and requires no language-model inference. Mean area under the receiver operating characteristic curve (AUROC) reaches 0.529 for Unseen Text and 0.554 for Unseen Reader on OneStop. Matched comparisons with AhnCNN show gains from both encoder redesign and lexical augmentation in these settings. Separate training and evaluation on SB-SAT also yield higher mean AUROC than AhnCNN. LEXIC occupies only 166 KB of model weights and requires 1.4 ms per trial on a single CPU core, supporting lightweight on-device inference.
Abstract:Predicting comprehension from eye movements could support adaptive reading interfaces. We present LEXIC, a compact recurrent model that predicts response correctness from fixation sequences, word frequency, and character length. It has 41.6K parameters and requires no language-model inference. Mean area under the receiver operating characteristic curve (AUROC) reaches 0.529 for Unseen Text and 0.554 for Unseen Reader on OneStop. Matched comparisons with AhnCNN show gains from both encoder redesign and lexical augmentation in these settings. Separate training and evaluation on SB-SAT also yield higher mean AUROC than AhnCNN. LEXIC occupies only 166 KB of model weights and requires 1.4 ms per trial on a single CPU core, supporting lightweight on-device inference.
Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)
arXiv:2607.08152 [cs.CL]
(or arXiv:2607.08152v2 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.08152 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 213 cuvinte
