Related papers: Adaptive Re-Ranking with a Corpus Graph
Retrieval-augmented generation (RAG) improves large language model reliability by grounding generated responses in external evidence. However, RAG performance depends on the relevance of retrieved passages, the quality of evidence ranking,…
Recent advancements in Large Language Models (LLMs) have transformed Natural Language Processing (NLP), enabling complex information retrieval and generation tasks. Retrieval-Augmented Generation (RAG) has emerged as a key innovation,…
Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages and multiple languages. Standard Retrieval-Augmented Generation (RAG) pipelines optimize…
A key component of fact verification is thevevidence retrieval, often from multiple documents. Recent approaches use dense representations and condition the retrieval of each document on the previously retrieved ones. The latter step is…
Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences. This is often more effective than pointwise re-ranking models that directly predict a relevance…
Numerous neural retrieval models have been proposed in recent years. These models learn to compute a ranking score between the given query and document. The majority of existing models are trained in pairwise fashion using human-judged…
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermediate computations are the same, we propose a pipeline-aware…
The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to…
Information retrieval systems such as open web search and recommendation systems are ubiquitous and significantly impact how people receive and consume online information. Previous research has shown the importance of fairness in…
Generative retrieval (GR) has emerged as a promising paradigm in recommendation systems by autoregressively decoding identifiers of target items. Despite its potential, current approaches typically rely on the next-token prediction schema,…
Multilingual retrieval-augmented generation (mRAG) is often implemented within a fixed retrieval space, typically via query or document translation or multilingual embedding vector representations. However, this approach may be inadequate…
Many recent approaches towards neural information retrieval mitigate their computational costs by using a multi-stage ranking pipeline. In the first stage, a number of potentially relevant candidates are retrieved using an efficient…
Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. [1] presented the first systematic evaluation comparing vector-based agentic RAG against…
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge, leading to improved accuracy and relevance. However, scaling RAG pipelines remains computationally expensive as retrieval sizes…
Search engines often follow a pipeline architecture, where complex but effective reranking components are used to refine the results of an initial retrieval. Retrieval augmented generation (RAG) is an exciting application of the pipeline…
Retrieval-augmented generation (RAG) is a promising method for addressing some of the memory-related challenges associated with Large Language Models (LLMs). Two separate systems form the RAG pipeline, the retriever and the reader, and the…
Retrieval-augmented large language models (LLMs) leverage relevant content retrieved by information retrieval systems to generate correct responses, aiming to alleviate the hallucination problem. However, existing retriever-responder…
We propose Referral-Augmented Retrieval (RAR), a simple technique that concatenates document indices with referrals, i.e. text from other documents that cite or link to the given document, to provide significant performance gains for…
Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for enhancing the performance of large language models (LLMs) by integrating external knowledge into the generation process. A key component of RAG pipelines is the…
We propose a scalable and cost-efficient framework for deploying Graph-based Retrieval-Augmented Generation (GraphRAG) in enterprise environments. While GraphRAG has shown promise for multi- hop reasoning and structured retrieval, its…