Zobrazeno 1 - 10
of 12 491
pro vyhledávání: '"Thomas, Paul A."'
Large-scale test collections play a crucial role in Information Retrieval (IR) research. However, according to the Cranfield paradigm and the research into publicly available datasets, the existing information retrieval research studies are commonly
Externí odkaz:
http://arxiv.org/abs/2408.16312
Autor:
Rahmani, Hossein A., Yilmaz, Emine, Craswell, Nick, Mitra, Bhaskar, Thomas, Paul, Clarke, Charles L. A., Aliannejadi, Mohammad, Siro, Clemencia, Faggioli, Guglielmo
The LLMJudge challenge is organized as part of the LLM4Eval workshop at SIGIR 2024. Test collections are essential for evaluating information retrieval (IR) systems. The evaluation and tuning of a search system is largely based on relevance labels, w
Externí odkaz:
http://arxiv.org/abs/2408.08896
Autor:
Rahmani, Hossein A., Siro, Clemencia, Aliannejadi, Mohammad, Craswell, Nick, Clarke, Charles L. A., Faggioli, Guglielmo, Mitra, Bhaskar, Thomas, Paul, Yilmaz, Emine
The first edition of the workshop on Large Language Model for Evaluation in Information Retrieval (LLM4Eval 2024) took place in July 2024, co-located with the ACM SIGIR Conference 2024 in the USA (SIGIR 2024). The aim was to bring information retriev
Externí odkaz:
http://arxiv.org/abs/2408.05388
Relevance labels, which indicate whether a search result is valuable to a searcher, are key to evaluating and optimising search systems. The best way to capture the true preferences of users is to ask them for their careful feedback on which results
Externí odkaz:
http://arxiv.org/abs/2309.10621
Thin-film solar cells reach high efficiencies and have a low carbon footprint in production. Tandem solar cells have the potential to significantly increase the efficiency of this technology, where the bottom-cell is generally composed of a Cu(In,Ga)
Externí odkaz:
http://arxiv.org/abs/2308.16103
Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike
Externí odkaz:
http://arxiv.org/abs/2308.06420
Autor:
Tsue, Trevor, Mombourquette, Brent, Taha, Ahmed, Matthews, Thomas Paul, Vu, Yen Nhi Truong, Su, Jason
This work reveals undiscovered challenges in the performance and generalizability of deep learning models. We (1) identify spurious shortcuts and evaluation issues that can inflate performance and (2) propose training and analysis methods to address
Externí odkaz:
http://arxiv.org/abs/2303.16417