什么触发了我的模型？对比解释说明翻译模型如何通过性别选择
What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models
AI总结：
研究通过对比翻译分析，揭示了翻译模型中性别选择的触发因素，并展示如何通过理解模型决策来减轻性别偏见。
摘要：
可解释性可以通过理解（黑盒）模型所做出的决定来实现，例如神经机器翻译（NMT）或大型语言模型（LLMs）。然而，这一领域的研究在这些模型中存在一个明显的问题：性别偏见。在本工作中，我们旨在从单纯测量偏见转向探索其起源。通过与性别中性自然源数据合作，这项探索性研究检查了哪种上下文，以输入令牌的形式出现在源句（EN）中，会影响NMT模型在目标语言（DE/ES）中选择特定性别变位。为了分析这一点，我们基于对比翻译计算了显著性归因。我们首先解决了缺乏评分阈值的挑战，并特别检查了源词的不同归因水平对模型性别决定的影响。我们还将显著的源词与人类对性别的感知进行比较，展示了人类感知与模型归因之间有明显的重叠。此外，我们还对显著词进行了语言分析。我们的工作展示了理解模型翻译决定在性别方面的相关性，以及这与人类决定的比较，并表明应利用这一信息来减轻性别偏见。
英文摘要：
Interpretability can be implemented to understand decisions taken by (black box) models, such as neural machine translation (NMT) or large language models (LLMs). Yet, research in this area has been limited in relation to a manifested problem in these models: gender bias. In this work, we aim to move away from simply measuring bias to exploring its origins. Working with gender-ambiguous natural source data, this exploratory study examines which context, in the form of input tokens in the source sentence (EN), influences (or triggers) the NMT model's choice of a certain gender inflection in the target languages (DE/ES). To analyse this, we compute saliency attribution based on contrastive translations. We first address the challenge of the lack of a scoring threshold and specifically examine different attribution levels of source words on the model's gender decisions in the translation. We compare salient source words with human perceptions of gender and demonstrate a noticeable overlap between human perceptions and model attribution. Additionally, we provide a linguistic analysis of salient words. Our work showcases the relevance of understanding model translation decisions in terms of gender, how this compares to human decisions and that this information should be leveraged to mitigate gender bias.
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。
