Conversational search utilizes muli-turn natural language contexts to
retrieve relevant passages. Existing conversational dense retrieval models
mostly view a conversation as a fixed sequence of questions and responses,
overlooking the severe data sparsity problem -- that is, users can perform a
conversation in various ways, and these alternate conversations are unrecorded.
Consequently, they often struggle to generalize to diverse conversations in
real-world scenarios. In this work, we propose a framework for generalizing
Conversational dense retrieval via LLM-cognition data Augmentation (ConvAug).
ConvAug first generates multi-level augmented conversations to capture the
diverse nature of conversational contexts. Inspired by human cognition, we
devise a cognition-aware process to mitigate the generation of false positives,
false negatives, and hallucinations. Moreover, we develop a difficulty-adaptive
sample filter that selects challenging samples for complex conversations,
thereby giving the model a larger learning space. A contrastive learning
objective is then employed to train a better conversational context encoder.
Extensive experiments conducted on four public datasets, under both normal and
zero-shot settings, demonstrate the effectiveness, generalizability, and
applicability of ConvAug.

通过 LLM - 认知数据增强（ConvAug）的方式，本文提出了一个泛化会话密集检索的框架，生成多级增强会话以捕捉会话上下文的多样性，利用认知感知过程减少误报、漏报和幻觉，通过难度自适应的样本筛选改进模型的学习空间，采用对比学习目标训练更好的会话上下文编码器。通过在四个公共数据集上进行广泛实验，包括正常设置和零样本设置，证明了 ConvAug 的有效性、泛化性和适用性。