Related papers: Enhancing Documents with Multidimensional Relevanc…
Reranking algorithms have made progress in improving document retrieval quality by efficiently aggregating relevance judgments generated by large language models (LLMs). However, identifying relevant documents for queries that require…
The strong capabilities of recent Large Language Models (LLMs) have made them highly effective for zero-shot re-ranking task. Attention-based re-ranking methods, which derive relevance scores directly from attention weights, offer an…
Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking…
Sparse annotation poses persistent challenges to training dense retrieval models; for example, it distorts the training signal when unlabeled relevant documents are used spuriously as negatives in contrastive learning. To alleviate this…
Multimodal document retrieval systems enable information access across text, images, and layouts, benefiting various domains like document-based question answering, report analysis, and interactive content summarization. Rerankers improve…
The crucial role of the evaluation in the development of the information retrieval tools is useful evidence to improve the performance of these tools and the quality of results that they return. However, the classic evaluation approaches…
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…
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…
Although considerable efforts have been devoted to transformer-based ranking models for document search, the relevance-efficiency tradeoff remains a critical problem for ad-hoc ranking. To overcome this challenge, this paper presents BECR…
Relevance feedback techniques assume that users provide relevance judgments for the top k (usually 10) documents and then re-rank using a new query model based on those judgments. Even though this is effective, there has been little…
Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that…
Query expansion is an effective approach for mitigating vocabulary mismatch between queries and documents in information retrieval. One recent line of research uses language models to generate query-related contexts for expansion. Along…
Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned…
The powerful generative abilities of large language models (LLMs) show potential in generating relevance labels for search applications. Previous work has found that directly asking about relevancy, such as ``How relevant is document A to…
Reranking is a critical stage in contemporary information retrieval (IR) systems, improving the relevance of the user-presented final results by honing initial candidate sets. This paper is a thorough guide to examine the changing reranker…
Contextual ranking models have delivered impressive performance improvements over classical models in the document ranking task. However, these highly over-parameterized models tend to be data-hungry and require large amounts of data even…
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…
Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep LMs can also be…
Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…
In content-based image retrieval, the first-round retrieval result by simple visual feature comparison may be unsatisfactory, which can be refined by visual re-ranking techniques. In image retrieval, it is observed that the contextual…