Related papers: DAPR: A Benchmark on Document-Aware Passage Retrie…
Temporal awareness is crucial in many information retrieval tasks, particularly in scenarios where the relevance of documents depends on their alignment with the query's temporal context. Traditional approaches such as BM25 and Dense…
In traditional RAG framework, the basic retrieval units are normally short. The common retrievers like DPR normally work with 100-word Wikipedia paragraphs. Such a design forces the retriever to search over a large corpus to find the…
Dense passage retrieval (DPR) models show great effectiveness gains in first stage retrieval for the web domain. However in the web domain we are in a setting with large amounts of training data and a query-to-passage or a query-to-document…
Recent advances have extended the context window of frontier LLMs dramatically, from a few thousand tokens up to millions, enabling entire books and codebases to fit into context. However, the compute costs of inferencing long-context LLMs…
Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However,…
Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over. Such methods struggle to adapt to the query-specific logic required for…
With over 200 million published academic documents and millions of new documents being written each year, academic researchers face the challenge of searching for information within this vast corpus. However, existing retrieval systems…
Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased computational overhead. Recently, Learned Sparse Retrieval (LSR)…
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…
Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond these shallow signals, recent benchmarks introduce…
According to common relevance-judgments regimes, such as TREC's, a document can be deemed relevant to a query even if it contains a very short passage of text with pertinent information. This fact has motivated work on passage-based…
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external documents at inference time, enabling up-to-date knowledge access without costly retraining. However, conventional RAG methods retrieve…
Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval…
Retrieved documents containing noise will hinder RAG from detecting answer clues and make the inference process slow and expensive. Therefore, context compression is necessary to enhance its accuracy and efficiency. Existing context…
Retrieval augmented generation (RAG) has been widely adopted to help Large Language Models (LLMs) to process tasks involving long documents. However, existing retrieval models are not designed for long document retrieval and fail to address…
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…
Dense passage retrieval (DPR) is the first step in the retrieval augmented generation (RAG) paradigm for improving the performance of large language models (LLM). DPR fine-tunes pre-trained networks to enhance the alignment of the…
AI systems have achieved remarkable success in processing text and relational data, yet visual document processing remains relatively underexplored. Whereas traditional systems require OCR transcriptions to convert these visual documents…
Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…
Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…