arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.00680cs.CL
收藏

用于语言歧义下的质量估计的Sigmoid头

Sigmoid Head for Quality Estimation under Language Ambiguity

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

Tu Anh Dinh, Jan Niehues

AI总结:

本文提出Sigmoid头模块,通过改进语言模型的概率估计方法,解决语言歧义导致的输出质量评估不准确问题,提升模型在非领域场景下的鲁棒性。

摘要:

语言模型(LM)的概率并非可靠的质量估计器,因为自然语言具有歧义性。当存在多个有效输出选项时,模型的概率分布会分散在这些选项上,可能误导性地表明输出质量低。这一问题由两个原因引起:(1)LM最终输出的激活是softmax,这不允许多个正确选项同时获得高概率;(2)LM的训练数据是单个的一热编码参考,表明每个输出步骤只有一个正确选项。我们提出在预训练LM上训练一个质量估计模块,以解决这些限制。该模块称为Sigmoid头,是一个带有sigmoid激活的额外解嵌头,用于解决第一个限制。为解决第二个限制,在训练Sigmoid头时进行负采样过程时,我们使用启发式方法避免选择可能的替代正确标记。Sigmoid头在训练和推理过程中计算效率高。与原始softmax头相比,Sigmoid头的概率提供了更明显的质量信号。由于Sigmoid头不依赖人工标注的质量数据,因此在非领域设置下比监督QE更稳健。

英文摘要:

Language model (LM) probability is not a reliable quality estimator, as natural language is ambiguous. When multiple output options are valid, the model's probability distribution is spread across them, which can misleadingly indicate low output quality. This issue is caused by two reasons: (1) LMs' final output activation is softmax, which does not allow multiple correct options to receive high probabilities simultaneuously and (2) LMs' training data is single, one-hot encoded references, indicating that there is only one correct option at each output step. We propose training a module for Quality Estimation on top of pre-trained LMs to address these limitations. The module, called Sigmoid Head, is an extra unembedding head with sigmoid activation to tackle the first limitation. To tackle the second limitation, during the negative sampling process to train the Sigmoid Head, we use a heuristic to avoid selecting potentially alternative correct tokens. Our Sigmoid Head is computationally efficient during training and inference. The probability from Sigmoid Head is notably better quality signal compared to the original softmax head. As the Sigmoid Head does not rely on human-annotated quality data, it is more robust to out-of-domain settings compared to supervised QE.

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。

↑