Learning to tokenize for generative retrieval
As a new paradigm in information retrieval, generative retrieval directly generates a ranked
list of document identifiers (docids) for a given query using generative language models …
list of document identifiers (docids) for a given query using generative language models …
From matching to generation: A survey on generative information retrieval
Information Retrieval (IR) systems are crucial tools for users to access information, widely
applied in scenarios like search engines, question answering, and recommendation …
applied in scenarios like search engines, question answering, and recommendation …
Recent advances in generative information retrieval
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 …
has witnessed significant growth recently. Compared to the traditional “index-retrieve-then …
Planning ahead in generative retrieval: Guiding autoregressive generation through simultaneous decoding
This paper introduces PAG-a novel optimization and decoding approach that guides
autoregressive generation of document identifiers in generative retrieval models through …
autoregressive generation of document identifiers in generative retrieval models through …
Scalable and effective generative information retrieval
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 …
indexes by representing each document as a sequence of document ID tokens. These …
Generative retrieval as multi-vector dense retrieval
For a given query generative retrieval generates identifiers of relevant documents in an end-
to-end manner using a sequence-to-sequence architecture. The relation between …
to-end manner using a sequence-to-sequence architecture. The relation between …
Listwise generative retrieval models via a sequential learning process
Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single
sequence-to-sequence model is learned to directly generate a list of relevant document …
sequence-to-sequence model is learned to directly generate a list of relevant document …
GLEN: Generative retrieval via lexical index learning
Generative retrieval shed light on a new paradigm of document retrieval, aiming to directly
generate the identifier of a relevant document for a query. While it takes advantage of …
generate the identifier of a relevant document for a query. While it takes advantage of …
Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation
Knowledge graph-grounded dialog generation requires retrieving a dialog-relevant
subgraph from the given knowledge base graph and integrating it with the dialog history …
subgraph from the given knowledge base graph and integrating it with the dialog history …
KTRL+ F: Knowledge-Augmented In-Document Search
We introduce a new problem KTRL+ F, a knowledge-augmented in-document search task
that necessitates real-time identification of all semantic targets within a document with the …
that necessitates real-time identification of all semantic targets within a document with the …