CoDi：面向接地问答的对话蒸馏
CoDi: Conversational Distillation for Grounded Question Answering
AI总结：
提出对话蒸馏框架CoDi，为约10亿参数的小语言模型合成大规模对话数据，在接地问答任务上达到与人工数据相当的性能，并超越更大规模指令微调模型。
摘要：
将对话技能蒸馏到参数约为10亿的小语言模型（SLM）中面临着重大挑战。首先，与较大模型相比，SLM的模型参数容量有限，难以学习广泛的知识。其次，高质量的对话数据集往往稀缺、规模小且局限于特定领域。针对这些挑战，我们提出了一种新颖的数据蒸馏框架，名为CoDi（Conversational Distillation的缩写，发音为“Cody”），该框架能够以可引导且多样化的方式合成大规模、助手风格的数据集。具体而言，尽管我们的框架在核心上是任务无关的，但我们探索并评估了CoDi在对话式接地推理问答任务上的潜力。这是专家型SLM的典型设备端场景，允许开放领域的模型响应，而无需模型在其有限的权重中“记忆”世界知识。我们的评估表明，使用CoDi合成数据训练的SLM在标准指标上达到了与使用人工标注数据训练的模型相当的性能。此外，当使用我们的框架从网络数据生成更大规模的数据集时，我们的模型在零样本对话式接地推理任务上超越了更大规模、经过指令微调的模型。
英文摘要：
Distilling conversational skills into Small Language Models (SLMs) with approximately 1 billion parameters presents significant challenges. Firstly, SLMs have limited capacity in their model parameters to learn extensive knowledge compared to larger models. Secondly, high-quality conversational datasets are often scarce, small, and domain-specific. Addressing these challenges, we introduce a novel data distillation framework named CoDi (short for Conversational Distillation, pronounced "Cody"), allowing us to synthesize large-scale, assistant-style datasets in a steerable and diverse manner. Specifically, while our framework is task agnostic at its core, we explore and evaluate the potential of CoDi on the task of conversational grounded reasoning for question answering. This is a typical on-device scenario for specialist SLMs, allowing for open-domain model responses, without requiring the model to "memorize" world knowledge in its limited weights. Our evaluations show that SLMs trained with CoDi-synthesized data achieve performance comparable to models trained on human-annotated data in standard metrics. Additionally, when using our framework to generate larger datasets from web data, our models surpass larger, instruction-tuned models in zero-shot conversational grounded reasoning tasks.
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。
