谁获得尊重？孟加拉语敬语分配偏差的反事实基准
Who Receives Respect? A Counterfactual Benchmark for Honorific Allocation Bias in Bengali
AI总结：
该研究构建了孟加拉语敬语分配偏差的反事实基准，评估9个语言模型在英语-孟加拉语翻译中敬语分配的偏差，发现职业对敬语选择的影响远大于性别，不同模型的偏差程度差异显著。
摘要：
孟加拉语没有语法性别，但敬语是强制性的：每一个第三人称指代都必须选择普通或尊敬语域。英语没有此类信号，因此系统必须选择源文本从未指定的尊重程度。我们利用这一特性来测量语言模型（LLMs）在英语-孟加拉语翻译中如何分配尊重。我们的评估集包含72种职业的2016个句子，每个句子在四个代词条件下有七个句子框架，阳性和阴性版本仅相差一个词，形成反事实对。我们为每个模型报告0-100分制的单一敬语偏差得分（HBS），涵盖性别和职业两个维度，得分越低表示尊重分配越均匀。在职业分析中，我们计算7个无代词句子框架中每种职业的敬语率，各模型的72种职业水平率的标准差在17.2至35.5个百分点之间，显示不同职业间敬语分配存在显著差异。职业与语域选择方差的关联度为3.2%至51.5%，而性别最多仅关联1.2%的方差。性别效应整体小得多：9个模型中仅有2个显示出显著的定向性别差距，且它们偏向相反的性别。9个模型的HBS在19.9至70.1之间，显示模型间尊重分配的均匀度存在显著差异。
英文摘要：
Bengali has no grammatical gender, but honorificity is obligatory: every third-person reference must choose ordinary or respectful register. English has no such signal, so the system must choose a level of deference that the source never specified. We use this property to measure how large language models (LLMs) allocate respect in English--Bengali translation. Our evaluation set contains 2{,}016 sentences across 72 occupations. Each appears in seven sentence frames under four pronoun conditions. Masculine and feminine versions differ by one word, forming counterfactual pairs. We report a single Honorific Bias Score (HBS) for each model on a 0--100 scale, covering both the gender and occupation axes. A lower score means that respect is allocated more evenly. For the occupation analysis, we compute each occupation's honorific rate across the seven no-pronoun sentence frames. The standard deviation of these 72 occupation-level rates ranges from 17.2 to 35.5 percentage points across models, showing substantial variation in how honorifics are allocated across occupations. Occupation is associated with 3.2\% to 51.5\% of the variance in register choice, compared with at most 1.2\% for gender. Gender effects are much smaller overall: only two of the nine models show significant directional gender gaps, and they favor opposite genders. HBS ranges from 19.9 to 70.1 across the nine models, showing substantial variation in how evenly the models allocate respect.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
