Metraipolis › archive › dc_7dea52d5aca7
How Much Can AI Understand? Toward AI-Assisted Sensemaking of Collaborative Discussion in Groups with Shared History — arXiv:2608.27799
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27799
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T10:47:56.479Z
- SHA-256 of the archived text
609c98ebec505b12ce54c0983ef14bdca9c28aa571305a2e0c8fe77778e1f370- Stable URL of this page
https://metraipolis.com/documento/dc_7dea52d5aca7
How to cite
How Much Can AI Understand? Toward AI-Assisted Sensemaking of Collaborative Discussion in Groups with Shared History — arXiv:2608.27799 — arXiv (en), https://arxiv.org/abs/2608.27799 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7dea52d5aca7 (Metraipolis archive dc_7dea52d5aca7, sha256 609c98ebec505b12ce54c0983ef14bdca9c28aa571305a2e0c8fe77778e1f370)
BibTeX
@misc{dc7dea52d5aca7,
title = {How Much Can AI Understand? Toward AI-Assisted Sensemaking of Collaborative Discussion in Groups with Shared History — arXiv:2608.27799},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27799},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7dea52d5aca7; sha256 609c98ebec505b12ce54c0983ef14bdca9c28aa571305a2e0c8fe77778e1f370},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27799. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI tools that support collaborative discussion typically treat the discussion as a standalone task, focusing only on its content and setting aside the social context of the group having it. But it is groups with a shared history, with their own norms, hierarchies, and relationships, where the most tangled and complex discussions tend to arise. These discussions cannot be understood apart from that context, and AI that overlooks it risks failing to convey what a discussion means, or even misrepresenting it. Drawing on two studies of how experienced Wikipedia editors read and make sense of discussions, we propose an AI-Assisted Sensemaking Model for Collaborative Discussions, which captures not only a discussion's arguments but also the norms and participants behind it, along with the context that gives each meaning. In this model, the system supports the early stages of the sensemaking process, and the degree to which it performs interpretive work can range from low to high. We argue that higher interpretive work reduces the burden on users but increases their reliance on the system's judgment. We then discuss the risks of an insufficiently intelligible system, what it would take to make one more intelligible, and the safeguards it still requires. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.AI). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.27799 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T10:33:42.471Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).