Generative retrieval (GR) has become a highly active area of information retrieval (IR) that has witnessed significant growth recently. Compared to the traditional “index-retrieve-then …
Recent research has shown that transformer networks can be used as differentiable search indexes by representing each document as a sequence of document ID tokens. These …
With the information explosion on the Web, search and recommendation are foundational infrastructures to satisfying users' information needs. As the two sides of the same coin, both …
Knowledge-intensive language tasks (KILTs) typically require retrieving relevant documents from trustworthy corpora, eg, Wikipedia, to produce specific answers. Very recently, a pre …
X Shi, J Liu, Y Liu, Q Cheng, W Lu - arXiv preprint arXiv:2310.12443, 2023 - arxiv.org
The advent of Large Language Models (LLMs) has shown the potential to improve relevance and provide direct answers in web searches. However, challenges arise in …
Automatic mainstream hashtag recommendation aims to accurately provide users with concise and popular topical hashtags before publication. Generally, mainstream hashtag …
S Wu, W Wei, M Zhang, Z Chen, J Ma, Z Ren… - arXiv preprint arXiv …, 2024 - arxiv.org
Generative retrieval generates identifiers of relevant documents in an end-to-end manner using a sequence-to-sequence architecture for a given query. The relation between …
This paper introduces PAG-a novel optimization and decoding approach that guides autoregressive generation of document identifiers in generative retrieval models through …
In this chapter, we consider generative information retrieval evaluation from two distinct but interrelated perspectives. First, large language models (LLMs) themselves are rapidly …