UKP-SQuARE v3: A Platform for Multi-Agent QA Research

Haritz Puerto, Tim Baumgärtner, Rachneet Sachdeva, Haishuo Fang, Hao Zhang, Sewin Tariverdian, Kexin Wang, Iryna Gurevych


Abstract
The continuous development of Question Answering (QA) datasets has drawn the research community’s attention toward multi-domain models. A popular approach is to use multi-dataset models, which are models trained on multiple datasets to learn their regularities and prevent overfitting to a single dataset. However, with the proliferation of QA models in online repositories such as GitHub or Hugging Face, an alternative is becoming viable. Recent works have demonstrated that combining expert agents can yield large performance gains over multi-dataset models. To ease research in multi-agent models, we extend UKP-SQuARE, an online platform for QA research, to support three families of multi-agent systems: i) agent selection, ii) early-fusion of agents, and iii) late-fusion of agents. We conduct experiments to evaluate their inference speed and discuss the performance vs. speed trade-off compared to multi-dataset models. UKP-SQuARE is open-source and publicly available.
Anthology ID:
2023.acl-demo.55
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Danushka Bollegala, Ruihong Huang, Alan Ritter
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
569–580
Language:
URL:
https://aclanthology.org/2023.acl-demo.55
DOI:
10.18653/v1/2023.acl-demo.55
Bibkey:
Cite (ACL):
Haritz Puerto, Tim Baumgärtner, Rachneet Sachdeva, Haishuo Fang, Hao Zhang, Sewin Tariverdian, Kexin Wang, and Iryna Gurevych. 2023. UKP-SQuARE v3: A Platform for Multi-Agent QA Research. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 569–580, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
UKP-SQuARE v3: A Platform for Multi-Agent QA Research (Puerto et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2023.acl-demo.55.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2023.acl-demo.55.mp4