Search Results for author: Graham Horwood

Found 5 papers, 0 papers with code

Active Evaluation Acquisition for Efficient LLM Benchmarking

no code implementations8 Oct 2024 Yang Li, Jie Ma, Miguel Ballesteros, Yassine Benajiba, Graham Horwood

Our approach models the dependencies across test examples, allowing accurate prediction of the evaluation outcomes for the remaining examples based on the outcomes of the selected ones.

Benchmarking

DoPAMine: Domain-specific Pre-training Adaptation from seed-guided data Mining

no code implementations30 Sep 2024 Vinayak Arannil, Neha Narwal, Sourav Sanjukta Bhabesh, Sai Nikhil Thirandas, Darren Yow-Bang Wang, Graham Horwood, Alex Anto Chirayath, Gouri Pandeshwar

Alternatively, in cases where domain data is available like healthcare and finance most of the LMs are proprietary necessitating the need for a scalable method to curate real world industry specific pre-training data.

Continual Pretraining Domain Adaptation +4

Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents

no code implementations11 Oct 2022 Muhammad Khalifa, Yogarshi Vyas, Shuai Wang, Graham Horwood, Sunil Mallya, Miguel Ballesteros

The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge.

Classification Document Classification +1

Macrocosm: Social Media Persona Linking for Open Source Intelligence Applications

no code implementations EMNLP 2019 Graham Horwood, Ning Yu, Thomas Boggs, Changjiang Yang, Chad Holvenstot

Online Social Networks (OSNs) provide a wealth of intelligence to analysts in assisting tasks such as tracking cyber-attacks, human trafficking activities, and misinformation campaigns.

Misinformation

Cannot find the paper you are looking for? You can Submit a new open access paper.