Metraipolis › archive › dc_e9e46bd183fd

arXiv 2610.13948: Can Language Models Play the Wikipedia Game?

Source
Metraipolis archive
Original
https://arxiv.org/abs/2610.13948
License (as archived)
CC-BY-4.0
Archived
2026-10-12T12:58:39.688Z
SHA-256 of the archived text
279b1157503d7d8f095e0e375e2a6e5f8075c2da133091073aa76a701042b9f7
Stable URL of this page
https://metraipolis.com/documento/dc_e9e46bd183fd

How to cite

arXiv 2610.13948: Can Language Models Play the Wikipedia Game? — Metraipolis archive, https://arxiv.org/abs/2610.13948 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_e9e46bd183fd (Metraipolis archive dc_e9e46bd183fd, sha256 279b1157503d7d8f095e0e375e2a6e5f8075c2da133091073aa76a701042b9f7)
BibTeX
@misc{dce9e46bd183fd,
  title = {arXiv 2610.13948: Can Language Models Play the Wikipedia Game?},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.13948},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_e9e46bd183fd; sha256 279b1157503d7d8f095e0e375e2a6e5f8075c2da133091073aa76a701042b9f7},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.13948. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowledge. We used the Wikipedia Game to test language models on an analogous information retrieval task. In the game, players must reach a target article using only article links. We compared sentence embedding models and LLMs across five Wikipedia languages and five academic-literature datasets. We construct very large local graphs of Wikipedia pages and of paper citations using OpenAlex and provide code to build and navigate them. This allows the study of language models' navigation capabilities without relying on third-party APIs. We compared the models with human and TF-IDF benchmarks. The Wikipedia Game format enables robust comparisons across techniques, languages, and domains. No model significantly outperformed humans, although the best models (GPT-o3 mini, GPT-4o, QwQ:32B, and DeepSeek-R1:70B) achieved comparable success. Performance and rankings varied across languages and topics, with implications for practitioners utilising these techniques.

Articolo: «Can Language Models Play the Wikipedia Game?» — Hickey, Alexander; Knight, Joanna; Bishop, James (2026-10-09), arXiv:2610.13948, categoria cs.AI (intelligenza artificiale).
Fonte: https://arxiv.org/abs/2610.13948
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-12T12:58:34Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.