Current interactive systems with natural language interfaces lack the ability to understand a complex information-seeking request which expresses several implicit constraints at once, and there is no prior information about user preferences e.g.,"find hiking trails around San Francisco which are accessible with toddlers and have beautiful scenery in summer", where output is a list of possible suggestions for users to start their exploration. In such scenarios, user requests can be issued in one shot in the form of a complex and long query, unlike conversational and exploratory search models, where require short utterances or queries are often presented to the system step by step. We have designed and deployed a platform to collect the data from approaching such complex interactive systems. Moreover, despite with the current advancement of generative language models these models suffer from hallucination in providing accurate factual knowledge. All language models are mostly trained in large part on web-scraped data from the past, which usually is not useful for immediate users' needs. In this article, we propose an IA that leverages Large Language Models (LLM) for complex request understanding and makes it interactive using Reinforcement learning that allows intricately refine user requests by making them complete, leading to better retrieval and reduce LLMs hallucination problems for current user needs. To demonstrate the performance of the proposed modeling paradigm, we have adopted various pre-retrieval metrics that capture the extent to which guided interactions with our system yield better retrieval results. Through extensive experimentation, we demonstrated that our method significantly outperforms several robust baselines.

翻译：当前具备自然语言界面的交互系统难以理解一次性表达多个隐式约束的复杂信息检索请求（例如“在旧金山周边寻找适合幼童徒步且夏季风景优美的步道”），此类场景中系统输出为供用户开始探索的候选建议列表，且缺乏用户偏好的先验信息。与对话式及探索性搜索模型不同——后者需用户逐步提供简短表述或查询——此类场景允许用户以复杂长查询形式一次性发出请求。我们设计并部署了一个数据采集平台，以探索此类复杂交互系统的实现路径。尽管生成式语言模型已取得显著进展，但其在提供准确事实性知识时仍存在幻觉问题：所有语言模型主要基于过往网络爬取数据训练，通常难以满足用户的即时需求。本文提出一种智能体架构，通过结合大型语言模型（LLM）实现复杂请求理解，并利用强化学习赋予系统交互能力——通过逐步完善用户请求的完整性实现精细化优化，从而提升检索效果并缓解LLM针对当前用户需求的幻觉问题。为验证所提出建模范式的性能，我们采用多种预检索指标，评估系统引导式交互对检索结果的提升幅度。大量实验证明，本方法显著优于多个稳健基线模型。