AI 中文总结
AfriSyCo通过母语与跨语言因子实验，测量断言性框架和验证对非洲语言内容答案切换的影响，发现断言显著增加错误目标选择，且效应受措辞和模型检查点强烈调节。
AI 中文摘要
AfriSyCo通过两个互补层面研究非洲语言事实内容周围的答案切换：母语后续提问和受控的跨语言因子设计，其中问题、选项和目标均保留非洲语言，而后续框架为英语。我们分析了从100个源问题中得出的1,415个首轮正确（turn-1-correct）的模型-语言-项目观测，涉及七个开放权重检查点和六种语言；首轮正确表示观测到的首次回答准确率，而非已证实的知识。在母语提示下，断言性认可（assertive endorsement）导致的任意轮次错误目标选择比提及加验证（M+V）高出29.3个百分点，即时T2对比为19.0个百分点。在预先承诺的2x2因子设计中，平均三种测试提示族，断言性框架使目标选择增加30.4个百分点（95%置信区间[28.4, 32.3]）；验证使其减少17.4个百分点，而断言效应从无验证时的20.5个百分点上升到有验证时的40.2个百分点（交互作用+19.7）。在选项重新排序后正确的611个观测中，效应仍为34.8个百分点。效应大小随措辞和检查点变化显著：提示族效应范围为20.1-42.5个百分点，Twi/Qwen3释义将目标选择从70.8%变为4.2%，检查点效应范围为9.2-47.0个百分点。因此，提示实现是测量问题的一部分。
英文摘要
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.
Comments13 pages, 1 figure, 9 tables
