EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automatically Correcting Large Language Models: Surveying the Landscape of Diverse Automated Correction Strategies

Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, William Yang Wang

Transactions of the Association for Computational Linguistics · 03.05.2024 · 12 · 484-506

DOI: 10.1162/tacl_a_00660 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 03.05.2024. Verfasst von Liangming Pan und 5 weiteren Autor:innen. Die Arbeit wurde bisher 104-mal zitiert (Crossref) und nennt 156 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While large language models (LLMs) have shown remarkable effectiveness in various NLP tasks, they are still prone to issues such as hallucination, unfaithful reasoning, and toxicity. A promising approach to rectify these flaws is correcting LLMs with feedback, where the LLM itself is prompted or guided with feedback to fix problems in its own output. Techniques leveraging automated feedback—either produced by the LLM itself (self-correction) or some external system—are of particular interest as they make LLM-based solutions more practical and deployable with minimal human intervention. This paper provides an exhaustive review of the recent advances in correcting LLMs with automated feedback, categorizing them into training-time, generation-time, and post-hoc approaches. We also identify potential challenges and future directions in this emerging field.

Zitieren

APA

Pan, L., Saxon, M., Xu, W., Nathani, D., Wang, X., & Wang, W. Y. (2024). Automatically Correcting Large Language Models: Surveying the Landscape of Diverse Automated Correction Strategies. Transactions of the Association for Computational Linguistics, 12, 484-506. https://doi.org/10.1162/tacl_a_00660

Vancouver

Pan L, Saxon M, Xu W, Nathani D, Wang X, Wang WY. Automatically Correcting Large Language Models: Surveying the Landscape of Diverse Automated Correction Strategies. Transactions of the Association for Computational Linguistics. 2024;12:484-506. doi:10.1162/tacl_a_00660

BibTeX
@article{Pan2024,
  author = {Pan, Liangming and Saxon, Michael and Xu, Wenda and Nathani, Deepak and Wang, Xinyi and Wang, William Yang},
  title = {Automatically Correcting Large Language Models: Surveying the Landscape of Diverse Automated Correction Strategies},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2024},
  volume = {12},
  pages = {484--506},
  doi = {10.1162/tacl_a_00660}
}
Kostenlos starten →