Related papers: dIR -- Discrete Information Retrieval: Conversatio…
Structured data offers a sophisticated mechanism for the organization of information. Existing methodologies for the text-serialization of structured data in the context of large language models fail to adequately address the heterogeneity…
This paper highlights the growing importance of information retrieval (IR) engines in the scientific community, addressing the inefficiency of traditional keyword-based search engines due to the rising volume of publications. The proposed…
Document retrieval is a key stage of standard Web search engines. Existing dual-encoder dense retrievers obtain representations for questions and documents independently, allowing for only shallow interactions between them. To overcome this…
Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable outputs, which are beyond single-shot prompting or standard…
Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a \emph{blind self-thinking} paradigm: performing extensive internal reasoning…
Making the content generated by Large Language Model (LLM), accurate, credible and traceable is crucial, especially in complex knowledge-intensive tasks that require multi-step reasoning and each step needs knowledge to solve.…
Conversational Search (CS) involves retrieving relevant documents from a corpus while considering the conversational context, integrating retrieval with context modeling. Recent advancements in Large Language Models (LLMs) have…
Recent work in cross-language information retrieval (CLIR), where queries and documents are in different languages, has shown the benefit of the Translate-Distill framework that trains a cross-language neural dual-encoder model using…
Web search provides a promising way for people to obtain information and has been extensively studied. With the surgence of deep learning and large-scale pre-training techniques, various neural information retrieval models are proposed and…
Composed Image Retrieval (CIR), which aims to find a target image from a reference image and a modification text, presents the core challenge of performing unified reasoning across visual and semantic modalities. While current approaches…
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…
Large language models (LLMs) are advancing rapidly. Such models have demonstrated strong capabilities in learning from large-scale (unstructured) text data and answering user queries. Users do not need to be experts in structured query…
The proliferation of long-form documents presents a fundamental challenge to information retrieval (IR), as their length, dispersed evidence, and complex structures demand specialized methods beyond standard passage-level techniques. This…
Query rewriting plays a vital role in enhancing conversational search by transforming context-dependent user queries into standalone forms. Existing approaches primarily leverage human-rewritten queries as labels to train query rewriting…
Recently, increasing attention has been focused on improving the ability of Large Language Models (LLMs) to perform complex reasoning. Advanced methods, such as Chain-of-Thought (CoT) and its variants, are found to enhance their reasoning…
Composed image retrieval (CIR) is the task of retrieving a target image specified by a query image and a relative text that describes a semantic modification to the query image. Existing methods in CIR struggle to accurately represent the…
Deploying accurate Text-to-SQL systems at the enterprise level faces a difficult trilemma involving cost, security and performance. Current solutions force enterprises to choose between expensive, proprietary Large Language Models (LLMs)…
Personalization in Information Retrieval (IR) is a topic studied by the research community since a long time. However, there is still a lack of datasets to conduct large-scale evaluations of personalized IR; this is mainly due to the fact…
Automatic detection of multimodal misinformation has gained a widespread attention recently. However, the potential of powerful Large Language Models (LLMs) for multimodal misinformation detection remains underexplored. Besides, how to…
Information Retrieval (IR) methods aim to identify documents relevant to a query, which have been widely applied in various natural language tasks. However, existing approaches typically consider only the textual content within documents,…