Two papers by TRAILS authors accepted to INLG 2024

22. Aug 2024 1 min read

Two papers from researchers in the TRAILS project have been accepted at the 17th International Natural Language Generation Conference (INLG 2024) that will take place September 23-27 in Tokyo, Japan. One paper presents a case study on using large language models to produce customer-friendly help page contents from more technical text, and includes a text quality evaluation by experienced editors. The other paper analyzes echo chamber effects in LLM-based chatbots in political conversations.

Aleksandra Gabryszak, Daniel Röder, Arne Binder, Luca Sion, Leonhard Hennig (2024). Enhancing Editorial Tasks: A Case Study on Rewriting Customer Help Page Contents Using Large Language Models. Proceedings of the 17th International Natural Language Generation Conference.

PDF Cite Dataset URL

Maximilian Bleick, Nils Feldhus, Aljoscha Burchardt, Sebastian Möller (2024). German Voter Personas can Radicalize LLM Chatbots via the Echo Chamber Effect. Proceedings of the 17th International Natural Language Generation Conference.

PDF Cite Code Dataset URL