Zobrazeno 1 - 10
of 9 319
pro vyhledávání: '"A. Azzopardi"'
Attributing answers to source documents is an approach used to enhance the verifiability of a model's output in retrieval augmented generation (RAG). Prior work has mainly focused on improving and evaluating the attribution quality of large language
Externí odkaz:
http://arxiv.org/abs/2410.12380
Autor:
Azzopardi, Shaun, Pace, Gordon
One can find various temporal deontic logics in literature, most focusing on discrete time. The literature on real-time constraints and deontic norms is much sparser. Thus, many analysis techniques which have been developed for deontic logics have no
Externí odkaz:
http://arxiv.org/abs/2410.12585
The morphologies of astronomical sources are highly complex, making it essential not only to classify the identified sources into their predefined categories but also to determine the sources that are most similar to a given query source. Image-based
Externí odkaz:
http://arxiv.org/abs/2410.08227
We introduce a novel computational unit, termed PushPull-Conv, in the first layer of a ResNet architecture, inspired by the anti-phase inhibition phenomenon observed in the primary visual cortex. This unit redefines the traditional convolutional laye
Externí odkaz:
http://arxiv.org/abs/2408.04077
Incomplete relevance judgments limit the re-usability of test collections. When new systems are compared against previous systems used to build the pool of judged documents, they often do so at a disadvantage due to the ``holes'' in test collection (
Externí odkaz:
http://arxiv.org/abs/2405.05600
TREC iKAT 2023: A Test Collection for Evaluating Conversational and Interactive Knowledge Assistants
Autor:
Aliannejadi, Mohammad, Abbasiantaeb, Zahra, Chatterjee, Shubham, Dalton, Jeffery, Azzopardi, Leif
Conversational information seeking has evolved rapidly in the last few years with the development of Large Language Models (LLMs), providing the basis for interpreting and responding in a naturalistic manner to user requests. The extended TREC Intera
Externí odkaz:
http://arxiv.org/abs/2405.02637
We present a translation from linear temporal logic with past to deterministic Rabin automata. The translation is direct in the sense that it does not rely on intermediate non-deterministic automata, and asymptotically optimal, resulting in Rabin aut
Externí odkaz:
http://arxiv.org/abs/2405.01178
Publikováno v:
The Second International Workshop on Conversational Approaches to Information Retrieval (CAIR 2018) at ACM SIGIR
The conversational search task aims to enable a user to resolve information needs via natural language dialogue with an agent. In this paper, we aim to develop a conceptual framework of the actions and intents of users and agents explaining how these
Externí odkaz:
http://arxiv.org/abs/2404.08630
Autor:
Azzopardi, Leif, Vinay, Vishwa
Publikováno v:
European Conference in Information Retrieval (ECIR) 2008
This paper introduces the concept of accessibility from the field of transportation planning and adopts it within the context of Information Retrieval (IR). An analogy is drawn between the fields, which motivates the development of document accessibi
Externí odkaz:
http://arxiv.org/abs/2404.08628
In most recent studies, gender bias in document ranking is evaluated with the NFaiRR metric, which measures bias in a ranked list based on an aggregation over the unbiasedness scores of each ranked document. This perspective in measuring the bias of
Externí odkaz:
http://arxiv.org/abs/2403.05975