"Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations", EMNLP2024

Repository for the experiments presented in "Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations", by Penzo N., Sajedinia M., Lepri B., Tonelli S., Guerini M., accepted at the Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024.

The diagnostic datasets provided in this repo are a subsample of the Ubuntu Internet Relay Chat Corpus by Ouchi and Tsuboi (2016).

• Paper: Hiroki Ouchi and Yuta Tsuboi. 2016. "Addressee and response selection for multi-party conversation." In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2133–2143, Austin, Texas. Association for Computational Linguistics.

• Repository: https://github.com/hiroki13/response-ranking

Part of the code is an adaptation of the code originally distributed in the previous repository (i.e., functions in "tools.py" int the subfolders "my_code").