Reversing the Death of Hypertext: Mechanistic Interpretability for LLM Navigation
ACM SIGWEB Newsletter · 01.01.2026 · 2026 (Winter) · 1-6
DOI: 10.1145/3801080.3801084 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM SIGWEB Newsletter, online erschienen am 31.03.2026. Verfasst von Wendy Zheng und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben.
Abstract (Originalsprache)
The rise of large language models (LLMs) has introduced a new mode of Web interaction called conversational navigation, in which autonomous agents retrieve and synthesize information into a single conversational response. While this offers significant efficiency gains, it conflicts with the architectural principles that originally structured the Web: visible links, discrete documents, user-directed traversal, and inspectable provenance. In doing so, these systems internalize processes that were once visible, obscuring from the user the very epistemic structure the Web was designed to preserve. Existing attempts to address this tension treat transparency as a surface problem, appending citations without reconsidering how LLMs relate to the Web's underlying structure. We propose mechanistic interpretability (MI) as a structural framework for realigning generative systems with the Web's epistemic commitments. Specifically, we analyze three stages at which MI techniques can render generative systems more inspectable: document retrieval, document ranking and integration, and provenance mapping from outputs to sources. Although MI does not restore traditional hypertext traversal, it can reintroduce traceability, visible grounding, and meaningful user agency within the generative paradigm.
Zitieren
APA
Zheng, W., He, Y., & Li, J. (2026). Reversing the Death of Hypertext: Mechanistic Interpretability for LLM Navigation. ACM SIGWEB Newsletter, 2026(Winter), 1-6. https://doi.org/10.1145/3801080.3801084
Vancouver
Zheng W, He Y, Li J. Reversing the Death of Hypertext: Mechanistic Interpretability for LLM Navigation. ACM SIGWEB Newsletter. 2026;2026(Winter):1-6. doi:10.1145/3801080.3801084
BibTeX
@article{Zheng2026,
author = {Zheng, Wendy and He, Yinhan and Li, Jundong},
title = {Reversing the Death of Hypertext: Mechanistic Interpretability for LLM Navigation},
journal = {ACM SIGWEB Newsletter},
year = {2026},
volume = {2026},
number = {Winter},
pages = {1--6},
doi = {10.1145/3801080.3801084}
}
EUVIMED