{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T17:51:59Z","timestamp":1774979519251,"version":"3.50.1"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"Winter","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGWEB Newsl."],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.1145\/3801080.3801084","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:58:18Z","timestamp":1774976298000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reversing the Death of Hypertext: Mechanistic Interpretability for LLM Navigation"],"prefix":"10.1145","volume":"2026","author":[{"given":"Wendy","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinhan","family":"He","sequence":"additional","affiliation":[{"name":"University of Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jundong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Virginia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"Bereska L. and Gavves E. 2024. Mechanistic interpretability for ai safety-a review. arXiv preprint arXiv:2404.14082."},{"key":"e_1_2_1_2_1","unstructured":"Berners-Lee T. J. 1989. Information management: A proposal. Tech. rep."},{"key":"e_1_2_1_3_1","unstructured":"Bommasani R. 2021. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258."},{"key":"e_1_2_1_4_1","volume-title":"How the machine 'thinks': Understanding opacity in machine learning algorithms. Big data & society 3, 1","author":"Burrell J.","year":"2053","unstructured":"Burrell, J. 2016. How the machine 'thinks': Understanding opacity in machine learning algorithms. Big data & society 3, 1, 2053951715622512."},{"key":"e_1_2_1_5_1","volume-title":"et al","author":"Bush V.","year":"1945","unstructured":"Bush, V. et al. 1945. As we may think. The atlantic monthly 176, 1, 101\u2013108."},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 1419\u20131436","author":"Chuang Y.-S.","unstructured":"Chuang, Y.-S., Qiu, L., Hsieh, C.-Y., Krishna, R., Kim, Y., and Glass, J. 2024. Lookback lens: Detecting and mitigating contextual hallucinations in large language models using only attention maps. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 1419\u20131436."},{"key":"e_1_2_1_7_1","volume-title":"Hypertext: An introduction and survey. Computer;(United States) 20, 9.","author":"Conklin J.","year":"1987","unstructured":"Conklin, J. 1987. Hypertext: An introduction and survey. Computer;(United States) 20, 9."},{"key":"e_1_2_1_8_1","unstructured":"Elhage N. Hume T. Olsson C. Schiefer N. Henighan T. Kravec S. Hatfield-Dodds Z. Lasenby R. Drain D. Chen C. et al. 2022. Toy models of superposition. arXiv preprint arXiv:2209.10652."},{"key":"e_1_2_1_9_1","first-page":"1","article-title":"A mathematical framework for transformer circuits","volume":"1","author":"Elhage N.","year":"2021","unstructured":"Elhage, N., Nanda, N., Olsson, C., Henighan, T., Joseph, N., Mann, B., Askell, A., Bai, Y., Chen, A., Conerly, T., et al. 2021. A mathematical framework for transformer circuits. Transformer Circuits Thread 1, 1, 12.","journal-title":"Transformer Circuits Thread"},{"key":"e_1_2_1_10_1","first-page":"9574","article-title":"Causal abstractions of neural networks","volume":"34","author":"Geiger A.","year":"2021","unstructured":"Geiger, A., Lu, H., Icard, T., and Potts, C. 2021. Causal abstractions of neural networks. Advances in Neural Information Processing Systems 34, 9574\u20139586.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Ji Z. Lee N. Frieske R. Yu T. Su D. Xu Y. Ishii E. Bang Y. J. Madotto A. and Fung P. 2023. Survey of hallucination in natural language generation. ACM computing surveys 55 12 1\u201338.","DOI":"10.1145\/3571730"},{"key":"e_1_2_1_12_1","volume-title":"-t","author":"Karpukhin V.","year":"2020","unstructured":"Karpukhin, V., Oguz, B., Min, S., Lewis, P. S., Wu, L., Edunov, S., Chen, D., and Yih, W.-t. 2020. Dense passage retrieval for open-domain question answering. In EMNLP (1). 6769\u20136781."},{"key":"e_1_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Kaushik A. and Jones G. J. 2023. Comparing conventional and conversational search interaction using implicit evaluation methods. arXiv preprint arXiv:2303.09258.","DOI":"10.5220\/0011798500003417"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the 60th annual meeting of the Association for Computational Linguistics (Volume 1: Long papers). 8460\u20138478","author":"Komeili M.","unstructured":"Komeili, M., Shuster, K., and Weston, J. 2022. Internet-augmented dialogue generation. In Proceedings of the 60th annual meeting of the Association for Computational Linguistics (Volume 1: Long papers). 8460\u20138478."},{"key":"e_1_2_1_15_1","volume-title":"HyperText: the convergence of contemporary critical theory and technology (parallax: re-visions of culture and society series)","author":"Landow G. P.","unstructured":"Landow, G. P. 1991. HyperText: the convergence of contemporary critical theory and technology (parallax: re-visions of culture and society series). Johns Hopkins University Press."},{"key":"e_1_2_1_16_1","unstructured":"Lazaridou A. Gribovskaya E. Stokowiec W. and Grigorev N. 2022. Internet-augmented language models through few-shot prompting for open-domain question answering. arXiv preprint arXiv:2203.05115."},{"key":"e_1_2_1_17_1","unstructured":"Lewis P. Perez E. Piktus A. Petroni F. Karpukhin V. Goyal N. K\u00fcttler H. Lewis M. Yih W.-t. Rockt\u00e4schel T. et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems 33 9459\u20139474."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"e_1_2_1_19_1","volume-title":"Weblinx: Real-world website navigation with multi-turn dialogue. arXiv preprint arXiv:2402.05930.","author":"L\u00f9 X. H.","year":"2024","unstructured":"L\u00f9, X. H., Kasner, Z., and Reddy, S. 2024. Weblinx: Real-world website navigation with multi-turn dialogue. arXiv preprint arXiv:2402.05930."},{"key":"e_1_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Maynez J. Narayan S. Bohnet B. and McDonald R. 2020. On faithfulness and factuality in abstractive summarization. arXiv preprint arXiv:2005.00661.","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Meng K. Bau D. Andonian A. and Belinkov Y. 2022. Locating and editing factual associations in gpt. Advances in neural information processing systems 35 17359\u201317372.","DOI":"10.52202\/068431-1262"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591871"},{"key":"e_1_2_1_23_1","volume-title":"Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332.","author":"Nakano R.","year":"2021","unstructured":"Nakano, R., Hilton, J., Balaji, S., Wu, J., Ouyang, L., Kim, C., Hesse, C., Jain, S., Kosaraju, V., Saunders, W., et al. 2021. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/800197.806036"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00024.001"},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of the 2017 conference on conference human information interaction and retrieval. 117\u2013126","author":"Radlinski F.","unstructured":"Radlinski, F. and Craswell, N. 2017. A theoretical framework for conversational search. In Proceedings of the 2017 conference on conference human information interaction and retrieval. 117\u2013126."},{"key":"e_1_2_1_27_1","volume-title":"Proceedings of the 2025 Adjunct Proceedings of the 36th ACM Conference on Hypertext and Social Media. 25\u201329","author":"Rahdari B.","unstructured":"Rahdari, B. and Brusilovsky, P. 2025. From links to dialogue; hypertext challenges and opportunities in conversational navigation. In Proceedings of the 2025 Adjunct Proceedings of the 36th ACM Conference on Hypertext and Social Media. 25\u201329."},{"key":"e_1_2_1_28_1","unstructured":"Rai D. Zhou Y. Feng S. Saparov A. and Yao Z. 2024. A practical review of mechanistic interpretability for transformer-based language models. arXiv preprint arXiv:2407.02646."},{"key":"e_1_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Shu D. Wu X. Zhao H. Rai D. Yao Z. Liu N. and Du M. 2025. A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models. arXiv preprint arXiv:2503.05613.","DOI":"10.18653\/v1\/2025.findings-emnlp.89"},{"key":"e_1_2_1_30_1","unstructured":"Spatharioti S. E. Rothschild D. M. Goldstein D. G. and Hofman J. M. 2023. Comparing traditional and llm-based search for consumer choice: A randomized experiment. arXiv preprint arXiv:2307.03744."},{"key":"e_1_2_1_31_1","volume-title":"Redeep: Detecting hallucination in retrieval-augmented generation via mechanistic interpretability. arXiv preprint arXiv:2410.11414.","author":"Sun Z.","year":"2024","unstructured":"Sun, Z., Zang, X., Zheng, K., Song, Y., Xu, J., Zhang, X., Yu, W., and Li, H. 2024. Redeep: Detecting hallucination in retrieval-augmented generation via mechanistic interpretability. arXiv preprint arXiv:2410.11414."},{"key":"e_1_2_1_32_1","unstructured":"Xiong G. He Z. Liu B. Sinha S. and Zhang A. 2025. Toward faithful retrieval-augmented generation with sparse autoencoders. arXiv preprint arXiv:2512.08892."}],"container-title":["ACM SIGWEB Newsletter"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801080.3801084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T16:58:23Z","timestamp":1774976303000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801080.3801084"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":32,"journal-issue":{"issue":"Winter","published-print":{"date-parts":[[2026,1,1]]}},"alternative-id":["10.1145\/3801080.3801084"],"URL":"https:\/\/doi.org\/10.1145\/3801080.3801084","relation":{},"ISSN":["1931-1745","1931-1435"],"issn-type":[{"value":"1931-1745","type":"print"},{"value":"1931-1435","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"assertion":[{"value":"2026-03-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}