Related papers: Generative and Pseudo-Relevant Feedback for Sparse…
Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain…
Building effective dense retrieval systems remains difficult when relevance supervision is not available. Recent work has looked to overcome this challenge by using a Large Language Model (LLM) to generate hypothetical documents that can be…
Retrieval-Augmented Generation (RAG) based on knowledge graphs (KGs) enhances large language models (LLMs) by providing structured and interpretable external knowledge. However, existing KG-based RAG methods struggle to retrieve accurate…
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…
Retrieval-augmented generation (RAG) frameworks enable large language models (LLMs) to retrieve relevant information from a knowledge base and incorporate it into the context for generating responses. This mitigates hallucinations and…
Conversational query reformulation (CQR) has become indispensable for improving retrieval in dialogue-based applications. However, existing approaches typically rely on reference passages for optimization, which are impractical to acquire…
Retrieval-Augmented Generation (RAG) is a crucial method for mitigating hallucinations in Large Language Models (LLMs) and integrating external knowledge into their responses. Existing RAG methods typically employ query rewriting to clarify…
Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that training objectives do not…
Despite its substantial impact on various search, recommendation, and question answering tasks, privacy-preserving methods for personalizing large language models (LLMs) have received relatively limited exploration. There is one primary…
Generative retrieval (GR) has emerged as a new paradigm in neural information retrieval, offering an alternative to dense retrieval (DR) by directly generating identifiers of relevant documents. In this paper, we theoretically and…
Text retrieval using learned dense representations has recently emerged as a promising alternative to "traditional" text retrieval using sparse bag-of-words representations. One recent work that has garnered much attention is the dense…
Large Language Models (LLMs) have shown remarkable reasoning capabilities, while their practical applications are limited by severe factual hallucinations due to limitations in the timeliness, accuracy, and comprehensiveness of their…
Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a subset of dimensions is consistently helpful for ranking.…
Retrieval-augmented code generation utilizes Large Language Models as the generator and significantly expands their code generation capabilities by providing relevant code, documentation, and more via the retriever. The current approach…
Pseudo-Random Numbers Generators (PRNGs) are algorithms produced to generate long sequences of statistically uncorrelated numbers, i.e. Pseudo-Random Numbers (PRNs). These numbers are widely employed in mid-level cryptography and in…
Vector-based retrieval systems have become a common staple for academic and industrial search applications because they provide a simple and scalable way of extending the search to leverage contextual representations for documents and…
We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are…
The goal of screening prioritisation in systematic reviews is to identify relevant documents with high recall and rank them in early positions for review. This saves reviewing effort if paired with a stopping criterion, and speeds up review…
By leveraging a dual encoder architecture, Dense Passage Retrieval (DPR) has outperformed traditional sparse retrieval algorithms such as BM25 in terms of passage retrieval accuracy. Recently proposed methods have further enhanced DPR's…
Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the…