现有的科学文档检索(SDR)方法主要依赖于从文档间关系中学习的文档中心表示来进行文档-文档(doc-doc)检索。然而,随着LLM和RAG的兴起,SDR逐渐转向以问题为导向的检索,其中文档是针对自然语言问题(q-doc)进行检索的。这种转变导致了文档中心模型与问题驱动检索之间的系统性不匹配,包括(1)输入粒度(长文档 vs. 短问题),(2)语义重点(科学论述结构 vs. 具体问题意图),以及(3)训练信号(引用基于的相似性 vs. 问题导向的相关性)。为此,我们提出了UniFAR,一种统一的面向面检索框架,以在单一架构内联合支持doc-doc和q-doc SDR。UniFAR通过自适应多粒度聚合解决粒度差异,通过可学习的面向锚点对齐文档结构与问题意图,并通过联合训练统一doc-doc和q-doc监督。实验结果表明,UniFAR在多个检索任务和基础模型上均优于先前方法,证实了其有效性和通用性。
英文摘要:
Scientific document retrieval (SDR) plays a critical role in modern scientific research, supporting knowledge discovery and evidence-based reasoning. It has evolved along two paradigms: document--document (doc-doc) retrieval driven by inter-document contrastive learning, and question--document (q-doc) retrieval emerging from LLMs and RAG for natural-language interaction. In practice, scientific workflows rely on both paradigms, requiring retrieval of related papers given a seed document and identifying relevant documents given a user question. However, existing methods typically treat these paradigms separately, hindering their complementary strengths. To address this, we propose UniFAR, a unified facet-aware retrieval framework that jointly supports doc-doc and q-doc retrieval within a shared representation space. UniFAR introduces a multi-granularity representation and aggregation module to unify the encoding of short questions and long documents, and a facet-level modeling mechanism with learnable anchors to capture structured semantic roles and complex user intents. It further adopts a facet-aware joint training strategy that integrates doc-doc and q-doc contrastive objectives with facet-level alignment, enabling unified learning from both inter-document relations and question-oriented supervision. Experiments on three benchmark datasets under both doc-doc and q-doc settings across multiple backbone models show that UniFAR consistently outperforms strong baselines and generalizes effectively across different backbones.
FLeW: Facet-Level and Adaptive Weighted Representation Learning of Scientific Documents
School of Computer Science, Beihang University(北航计算机学院);Beihang University(北航);Institute of Artificial Intelligence, Beihang University(北航人工智能研究院);Zhongguancun Laboratory(中关村实验室);National Computer Network Emergency Response Technical Team/Coordination Center of China(中国计算机网络应急技术攻关团队/协调中心)
PairSem: LLM-Guided Pairwise Semantic Matching for Scientific Document Retrieval
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Korea University(高丽大学);National Institutes of Health(美国国立卫生研究院);Pohang University of Science and Technology(浦项科技大学)
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
Università della Svizzera italiana (USI)(瑞士意大利语区大学(USI));University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校)
用户往往无法在一个查询中表达其复杂的信息需求。因此,他们可能需要扫描多个结果页面或重新制定他们的查询,这可能是一个令人沮丧的经历。或者,系统可以通过主动询问用户的问题来澄清他们的信息需求,从而提高用户满意度。在会话系统中,提出澄清性问题尤其重要,因为它们只能返回有限数量的结果(通常只有一个)。在本文中,我们制定了开放域信息寻求会话系统中的问题澄清的任务。为此,我们提出了一种离线评估方法,并通过众包收集了一个名为Qulac的数据集。我们的数据集建立在TREC Web Track 2009-2012数据的基础上,由198个TREC主题的10 K多个问答对组成,涉及762个方面。我们在Oracle模型上的实验表明,只问一个好问题,就P@1而言,检索性能提高了170%以上,这清楚地表明了任务的潜在影响。我们进一步提出了一个检索框架,包括三个组成部分:问题检索,问题选择,和文档检索。特别是,我们的问题选择模型考虑到原始查询和以前的问答互动,同时选择下一个问题。我们的模型显著优于竞争基准。为了促进这一领域的研究,我们公开了Qulac。