Users often make ambiguous requests that require clarification. We study the
problem of asking clarification questions in an information retrieval setting,
where systems often face ambiguous search queries and it is challenging to turn
the uncertainty in the retrieval model into a natural language question. We
present CLARINET, a system that asks informative clarification questions by
choosing questions whose answers would maximize certainty in the correct
candidate. Our approach works by augmenting a large language model (LLM) to
condition on a retrieval distribution, finetuning end-to-end to generate the
question that would have maximized the rank of the true candidate at each turn.
When evaluated on a real-world retrieval dataset of users searching for books,
our system outperforms traditional heuristics such as information gain on
retrieval success by 17% and vanilla-prompted LLMs by 39% relative.

这篇研究论文介绍了 CLARINET，一种能够通过选择问题来最大化正确候选项准确性的系统，在信息检索环境中提出澄清问题的问题，相对于传统的启发式方法提高了 17% 的检索成功率，并相对于简单提示的大型语言模型提高了 39%。

CLARINET：为检索任务扩展语言模型以提问澄清问题

CLARINET: Augmenting Language Models to Ask Clarification Questions for  Retrieval

Prompt tuning attempts to update few task-specific parameters in pre-trained
models. It has achieved comparable performance to fine-tuning of the full
parameter set on both language understanding and generation tasks. In this
work, we study the problem of prompt tuning for neural text retrievers. We
introduce parameter-efficient prompt tuning for text retrieval across
in-domain, cross-domain, and cross-topic settings. Through an extensive
analysis, we show that the strategy can mitigate the two issues --
parameter-inefficiency and weak generalizability -- faced by fine-tuning based
retrieval methods. Notably, it can significantly improve the out-of-domain
zero-shot generalization of the retrieval models. By updating only 0.1% of the
model parameters, the prompt tuning strategy can help retrieval models achieve
better generalization performance than traditional methods in which all
parameters are updated. Finally, to facilitate research on retrievers'
cross-topic generalizability, we curate and release an academic retrieval
dataset with 18K query-results pairs in 87 topics, making it the largest
topic-specific one to date.

本文介绍了一种基于 Prompt tuning 的神经文本检索方法，通过更新其中 0.1% 的参数，能够显著提高检索模型的泛化性能，在额外引入一份包括 87 个主题的来自学术领域的数据集的情况下，证明了这种检索方法的横向主题泛化性强于传统方法。