上下文相关的指令微调用于对话响应生成
Context-dependent Instruction Tuning for Dialogue Response Generation
AI总结：
针对多轮对话中固定指令失效的问题，提出基于上下文的指令微调框架，动态生成指令引导响应，在基准上以更低计算成本取得相当或更优性能。
摘要：
最近的语言模型通过在微调时将指令与任务输入相结合，在自然语言任务中取得了令人瞩目的性能。由于同一自然语言任务中的所有样本可以用相同的任务指令来解释，许多指令数据集仅为整个任务提供少量指令，而不考虑任务中每个示例的输入。然而，这种方法在复杂的多轮对话生成任务中变得无效，因为随着对话上下文的变化，每轮的输入变化很大，简单的任务指令无法提高生成性能。为了解决这一局限性，我们引入了一种基于上下文的指令微调框架，用于每个多轮对话，该框架基于之前的上下文作为输入来生成响应和指令。在评估期间，模型基于之前的上下文生成指令以自我引导响应。通过在对话基准数据集上的定量评估，该框架通过将指令与微调期间的输入对齐，在减少计算预算的情况下，与基线相比产生了相当甚至出色的结果。
英文摘要：
Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task instructions, many instruction datasets only provide a few instructions for the entire task, without considering the input of each example in the task. However, this approach becomes ineffective in complex multi-turn dialogue generation tasks, where the input varies highly with each turn as the dialogue context changes, so that simple task instructions cannot improve the generation performance. To address this limitation, we introduce a context-based instruction fine-tuning framework for each multi-turn dialogue which generates both responses and instructions based on the previous context as input. During the evaluation, the model generates instructions based on the previous context to self-guide the response. The proposed framework produces comparable or even outstanding results compared to the baselines by aligning instructions to the input during fine-tuning with the instructions in quantitative evaluations on dialogue benchmark datasets with reduced computation budget.
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。
