Recent approaches have explored language-guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instructions or prompts (Sanh et al., 2022; R. Menon et al., 2022). While these classifiers can generalize in zero-shot settings, their task performance often varies substantially between different language explanations in unpredictable ways (Lu et al., 2022; Gonen et al., 2022). Also, current approaches fail to leverage unlabeled examples that may be available in many scenarios. Here, we introduce TALC, a framework that uses data programming to adapt a language-guided classifier for a new task during inference when provided with explanations from multiple teachers and unlabeled test examples. Our results show that TALC consistently outperforms a competitive baseline from prior work by an impressive 9.3% (relative improvement). Further, we demonstrate the robustness of TALC to variations in the quality and quantity of provided explanations, highlighting its potential in scenarios where learning from multiple teachers or a crowd is involved. Our code is available at: https://github.com/WeiKangda/TALC.git.

翻译：近期研究探索了语言引导分类器，这类分类器在获得任务特定的自然语言解释、指令或提示时，能够对新任务中的样本进行分类（Sanh 等，2022；R. Menon 等，2022）。尽管这些分类器能在零样本设置下泛化，但不同语言解释间的任务性能常呈现不可预测的显著差异（Lu 等，2022；Gonen 等，2022）。此外，当前方法未能利用许多场景中可用的无标签样本。本文提出 TALC 框架，该框架采用数据编程方法，在推理阶段通过融合多位教师提供的解释与无标签测试样本，自适应调整语言引导分类器以适应新任务。结果显示，TALC 持续超越先前工作的竞争基线，相对提升达 9.3%。进一步，我们证明了 TALC 对解释质量及数量变化的鲁棒性，突显其在涉及多位教师或群体学习场景中的潜力。代码开源地址：https://github.com/WeiKangda/TALC.git。