EUVIMEDEUVIMED entdecken
Crossref

Concept Matching with Agent for Out-of-Distribution Detection

Yuxiao Lee, Xiaofeng Cao, Jingcai Guo, Wei Ye, Qing Guo, Yi Chang

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (5) · 4562-4570

DOI: 10.1609/aaai.v39i5.32481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yuxiao Lee und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The remarkable achievements of Large Language Models (LLMs) have captivated the attention of both academia and industry, transcending their initial role in dialogue generation. To expand the usage scenarios of LLM, some works enhance the effectiveness and capabilities of the model by introducing more external information, which is called the agent paradigm. Based on this idea, we propose a new method that integrates the agent paradigm into out-of-distribution (OOD) detection task, aiming to improve its robustness and adaptability. Our proposed method, Concept Matching with Agent (CMA), employs neutral prompts as agents to augment the CLIP-based OOD detection process. These agents function as dynamic observers and communication hubs, interacting with both In-distribution (ID) labels and data inputs to form vector triangle relationships. This triangular framework offers a more nuanced approach than the traditional binary relationship, allowing for better separation and identification of ID and OOD inputs. Our extensive experimental results showcase the superior performance of CMA over both zero-shot and training-required methods in a diverse array of real-world scenarios.

Zitieren

APA

Lee, Y., Cao, X., Guo, J., Ye, W., Guo, Q., & Chang, Y. (2025). Concept Matching with Agent for Out-of-Distribution Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(5), 4562-4570. https://doi.org/10.1609/aaai.v39i5.32481

Vancouver

Lee Y, Cao X, Guo J, Ye W, Guo Q, Chang Y. Concept Matching with Agent for Out-of-Distribution Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(5):4562-4570. doi:10.1609/aaai.v39i5.32481

BibTeX
@article{Lee2025,
  author = {Lee, Yuxiao and Cao, Xiaofeng and Guo, Jingcai and Ye, Wei and Guo, Qing and Chang, Yi},
  title = {Concept Matching with Agent for Out-of-Distribution Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {5},
  pages = {4562--4570},
  doi = {10.1609/aaai.v39i5.32481}
}
Kostenlos starten →