Related papers: ReFIT: Relevance Feedback from a Reranker during I…

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…

Retrieve-and-rerank is a popular retrieval pipeline because of its ability to make slow but effective rerankers efficient enough at query time by reducing the number of comparisons. Recent works in neural rerankers take advantage of large…

Passage reranking is a critical task in various applications, particularly when dealing with large volumes of documents. Existing neural architectures have limitations in retrieving the most relevant passage for a given question because the…

Modern retrieval pipelines increasingly rely on query reformulation and neural reranking to improve effectiveness, but this comes at a significant computational cost and introduces a fundamental tradeoff between recall and query drift.…

Large Language Models (LLMs) have significantly advanced the field of information retrieval, particularly for reranking. Listwise LLM rerankers have showcased superior performance and generalizability compared to existing supervised…

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 models encode pointers to information in a corpus as an index within the model's parameters. These models serve as part of a larger pipeline, where retrieved information conditions generation for knowledge-intensive NLP…

Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach…

Modern large-scale recommender systems employ multi-stage ranking funnel (Retrieval, Pre-ranking, Ranking) to balance engagement and computational constraints (latency, CPU). However, the initial retrieval stage, often relying on efficient…

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model…

Rerankers, typically cross-encoders, are computationally intensive but are frequently used because they are widely assumed to outperform cheaper initial IR systems. We challenge this assumption by measuring reranker performance for full…

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on…

Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and…

Response retrieval is a subset of neural ranking in which a model selects a suitable response from a set of candidates given a conversation history. Retrieval-based chat-bots are typically employed in information seeking conversational…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…

LLMs confront inherent limitations in terms of its knowledge, memory, and action. The retrieval augmentation stands as a vital mechanism to address these limitations, which brings in useful information from external sources to augment the…

Ranking consistently emerges as a primary focus in information retrieval research. Retrieval and ranking models serve as the foundation for numerous applications, including web search, open domain QA, enterprise domain QA, and text-based…

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…