Related papers: Doc2Query++: Topic-Coverage based Document Expansi…

One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content.From the perspective of a question answering system, this might comprise…

Knowledge-intensive multi-hop question answering (QA) tasks, which require integrating evidence from multiple sources to address complex queries, often necessitate multiple rounds of retrieval and iterative generation by large language…

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

Large-scale digitization initiatives have unlocked massive collections of historical newspapers, yet effective computational access remains hindered by OCR corruption, multilingual orthographic variation, and temporal language drift. We…

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR…

Multimodal documents contain diverse elements, such as tables, figures, and layouts, which can complicate retrieval tasks. While current approaches typically combine dense visual embedding models with supervised rerankers to achieve…

Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text settings. Traditional discriminative models are constrained…

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…

One of the challenges in information retrieval (IR) is the vocabulary mismatch problem, which happens when the terms between queries and documents are lexically different but semantically similar. While recent work has proposed to expand…

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding capabilities of LLMs, most existing LLM-based rerankers rely…

Patient-trial matching requires reasoning over long, heterogeneous electronic health records (EHRs) and complex eligibility criteria, posing significant challenges for scalability, generalization, and computational efficiency. Existing…

The key challenge in semantic search is to create models that are both accurate and efficient in pinpointing relevant sentences for queries. While BERT-style bi-encoders excel in efficiency with pre-computed embeddings, they often miss…

Large Language Models (LLMs) are foundational in language technologies, particularly in information retrieval (IR). Previous studies have utilized LLMs for query expansion, achieving notable improvements in IR. In this paper, we thoroughly…

Recent studies show the growing significance of document retrieval in the generation of LLMs, i.e., RAG, within the scientific domain by bridging their knowledge gap. However, dense retrievers often struggle with domain-specific retrieval…

Pre-trained language models have achieved promising success in code retrieval tasks, where a natural language documentation query is given to find the most relevant existing code snippet. However, existing models focus only on optimizing…

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…

Retrieval-Augmented Generation (RAG) systems using Multimodal Large Language Models (MLLMs) show great promise for complex document understanding, yet their development is critically hampered by inadequate evaluation. Current benchmarks…

We present the DEREK (Deep Extraction & Reasoning Engine for Knowledge) Module, a secure and scalable Retrieval-Augmented Generation pipeline designed specifically for enterprise document question answering. Designed and implemented by…

This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access". The goal of the task is to generate…