Breaking the Linear Barrier: A Multi-Modal LLM-Based System for Navigating Complex Web Content
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Visually impaired users still face fundamental obstacles when interacting with complex, dynamic websites. Conventional screen readers expose pages in a strict linear order, offer little semantic context for visual media, and provide limited context regarding the page content. This paper introduces a multi-modal accessibility framework combining Large Language Models (LLMs), Computer Vision, and dynamic DOM manipulation to significantly enhance semantic clarity, non-linear navigation, and interaction richness. By interpreting visual and textual web content contextually and adapting it into an intuitive, conversationally navigable interface, our method provides a foundation for visually impaired users to interact effectively with previously inaccessible or challenging digital experiences.The deployment of a functional prototype on a modern web browser illustrates the capability of the proposed system to interact with diverse websites and tasks. The research team selected Canada’s most frequented websites to assess the system’s efficacy in enhancing contextual understanding of the page content and enabling navigation through pages and actions via a chat-driven interface. A comprehensive demonstration was executed using a prominent ticketing site, which facilitated users in obtaining a deeper understanding of the page while guiding them towards the successful purchase of concert tickets. By illustrating how vision language and LLM reasoning can be coupled with low-level browser control, this work lays the groundwork for future efforts in performance optimization, large-scale evaluation, and personalization across diverse web contexts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it