Metraipolis › archive › dc_bb5c013dd0a3

AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content — arXiv:2609.17853

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17853
License (as archived)
CC0-1.0
Archived
2026-10-15T13:49:16.931Z
SHA-256 of the archived text
8b22c89fafb2dac24358c54483e363d9a364dc21f1074ee36547e87198a9d92b
Stable URL of this page
https://metraipolis.com/documento/dc_bb5c013dd0a3

How to cite

AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content — arXiv:2609.17853 — arXiv (en), https://arxiv.org/abs/2609.17853 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb5c013dd0a3 (Metraipolis archive dc_bb5c013dd0a3, sha256 8b22c89fafb2dac24358c54483e363d9a364dc21f1074ee36547e87198a9d92b)
BibTeX
@misc{dcbb5c013dd0a3,
  title = {AfriSyCo: Measuring Assertive Framing, Verification, and Wording Sensitivity Around African-Language Content — arXiv:2609.17853},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17853},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb5c013dd0a3; sha256 8b22c89fafb2dac24358c54483e363d9a364dc21f1074ee36547e87198a9d92b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17853. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AfriSyCo studies answer switching around African-language factual content with two complementary layers: native-language follow-ups and a controlled cross-language factorial whose question, options, and target remain in the African language while the follow-up framing is English. We analyze 1,415 turn-1-correct model-language-item observations derived from 100 source questions across seven open-weight checkpoints and six languages; turn-1-correct denotes observed first-response accuracy, not demonstrated knowledge. Under native prompts, assertive endorsement produces 29.3 percentage points more any-turn false-target selection than mention-plus-verification (M+V), with a 19.0-point immediate T2 contrast. In the precommitted 2 x 2 factorial, averaged over three tested prompt families, assertive framing increases target selection by 30.4 points (95% CI [28.4, 32.3]); verification decreases it by 17.4 points, while the assertive effect rises from 20.5 points without verification to 40.2 with it (interaction +19.7). The effect remains 34.8 points among 611 observations correct after option reordering. Magnitude varies sharply by wording and checkpoint: prompt-family effects span 20.1-42.5 points, a Twi/Qwen3 paraphrase shifts target selection from 70.8% to 4.2%, and checkpoint effects span 9.2-47.0 points. Prompt realization is therefore part of the measurement problem.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.17853 — 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 2026-10-15T13:48:24.282Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).