Metraipolis › archive › dc_8019cc6e69cc

Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space — arXiv:2609.29183

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29183
License (as archived)
CC0-1.0
Archived
2026-10-08T04:49:27.426Z
SHA-256 of the archived text
88fe9de62e9b16d153fca1c3820cbd7a276f4ee29667278066acde17dc896458
Stable URL of this page
https://metraipolis.com/documento/dc_8019cc6e69cc

How to cite

Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space — arXiv:2609.29183 — arXiv (en), https://arxiv.org/abs/2609.29183 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8019cc6e69cc (Metraipolis archive dc_8019cc6e69cc, sha256 88fe9de62e9b16d153fca1c3820cbd7a276f4ee29667278066acde17dc896458)
BibTeX
@misc{dc8019cc6e69cc,
  title = {Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space — arXiv:2609.29183},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29183},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8019cc6e69cc; sha256 88fe9de62e9b16d153fca1c3820cbd7a276f4ee29667278066acde17dc896458},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29183. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, however, they appear as scattered points in embedding space and are difficult to distinguish from ordinary noise without the benefit of hindsight. We study whether such anticipatory outliers can be predicted prospectively, using only information available when a document first appears. We derive labels from the subsequent trajectories of outlier documents, distinguishing those that anticipate new topics from those that reinforce existing topics or remain isolated, and estimate label confidence through agreement across multiple embedding models. On two French news corpora, anticipatory outliers prove predictable at publication time. Under cross-validation, $F_1$ rises from about 0.77 over the full eligible population to above 0.90 on high-consensus subsets, and remains at 0.76-0.80 under a strictly chronological evaluation. Predictive performance is driven mainly by geometric features capturing each outlier's position in embedding space.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.29183 — 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 2026-10-08T04:27:20.036Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).