Pitfalls of Conversational LLMs on News Debiasing

Ipek Baris Schlicht, Defne Altiok, Maryanne Taouk, Lucie Flek


Abstract
This paper addresses debiasing in news editing and evaluates the effectiveness of conversational Large Language Models in this task. We designed an evaluation checklist tailored to news editors’ perspectives, obtained generated texts from three popular conversational models using a subset of a publicly available dataset in media bias, and evaluated the texts according to the designed checklist. Furthermore, we examined the models as evaluator for checking the quality of debiased model outputs. Our findings indicate that none of the LLMs are perfect in debiasing. Notably, some models, including ChatGPT, introduced unnecessary changes that may impact the author’s style and create misinformation. Lastly, we show that the models do not perform as proficiently as domain experts in evaluating the quality of debiased outputs.
Anthology ID:
2024.delite-1.4
Volume:
Proceedings of the First Workshop on Language-driven Deliberation Technology (DELITE) @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Annette Hautli-Janisz, Gabriella Lapesa, Lucas Anastasiou, Valentin Gold, Anna De Liddo, Chris Reed
Venue:
DELITE
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
33–38
Language:
URL:
https://aclanthology.org/2024.delite-1.4
DOI:
Bibkey:
Cite (ACL):
Ipek Baris Schlicht, Defne Altiok, Maryanne Taouk, and Lucie Flek. 2024. Pitfalls of Conversational LLMs on News Debiasing. In Proceedings of the First Workshop on Language-driven Deliberation Technology (DELITE) @ LREC-COLING 2024, pages 33–38, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Pitfalls of Conversational LLMs on News Debiasing (Baris Schlicht et al., DELITE 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.delite-1.4.pdf