Related papers: LLM-VPRF: Large Language Model Based Vector Pseudo…

Scaling dense retrievers to larger large language model (LLM) backbones has been a dominant strategy for improving their retrieval effectiveness. However, this has substantial cost implications: larger backbones require more expensive…

Pseudo Relevance Feedback (PRF) is known to improve the effectiveness of bag-of-words retrievers. At the same time, deep language models have been shown to outperform traditional bag-of-words rerankers. However, it is unclear how to…

Large vision-language models (VLMs) enable intuitive visual search using natural language queries. However, improving their performance often requires fine-tuning and scaling to larger model variants. In this work, we propose a mechanism…

Pseudo-relevance feedback (PRF) can enhance average retrieval effectiveness over a sufficiently large number of queries. However, PRF often introduces a drift into the original information need, thus hurting the retrieval effectiveness of…

Pseudo-relevance feedback (PRF) methods built on large language models (LLMs) can be organized along two key design dimensions: the feedback source, which is where the feedback text is derived from and the feedback model, which is how the…

Query rewriting is a fundamental technique in information retrieval (IR). It typically employs the retrieval result as relevance feedback to refine the query and thereby addresses the vocabulary mismatch between user queries and relevant…

Pseudo-relevance feedback (PRF) is a classical approach to address lexical mismatch by enriching the query using first-pass retrieval. Moreover, recent work on generative-relevance feedback (GRF) shows that query expansion models using text…

This paper considers Pseudo-Relevance Feedback (PRF) methods for dense retrievers in a resource constrained environment such as that of cheap cloud instances or embedded systems (e.g., smartphones and smartwatches), where memory and CPU are…

Pseudo-relevance feedback (PRF) is commonly used to boost the performance of traditional information retrieval (IR) models by using top-ranked documents to identify and weight new query terms, thereby reducing the effect of query-document…

Query expansion is a long-standing technique to mitigate vocabulary mismatch in ad hoc Information Retrieval. Pseudo-relevance feedback methods, such as RM3, estimate an expanded query model from the top-ranked documents, but remain…

Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set of retrieved documents, known as the…

Recently embedding-based retrieval or dense retrieval have shown state of the art results, compared with traditional sparse or bag-of-words based approaches. This paper introduces a model-agnostic doc-level embedding framework through large…

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…

Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent…

Current query expansion models use pseudo-relevance feedback to improve first-pass retrieval effectiveness; however, this fails when the initial results are not relevant. Instead of building a language model from retrieved results, we…

Retrieval augmentation is critical when Language Models (LMs) exploit non-parametric knowledge related to the query through external knowledge bases before reasoning. The retrieved information is incorporated into LMs as context alongside…

Pretrained language models like BERT and T5 serve as crucial backbone encoders for dense retrieval. However, these models often exhibit limited generalization capabilities and face challenges in improving in domain accuracy. Recent research…

Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From classic retrieval methods to learning-based ranking…

In this work, we propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…