@inproceedings{kunz-kuhlmann-2024-properties,
title = "Properties and Challenges of {LLM}-Generated Explanations",
author = "Kunz, Jenny and
Kuhlmann, Marco",
editor = "Blodgett, Su Lin and
Curry, Amanda Cercas and
Dey, Sunipa and
Madaio, Michael and
Nenkova, Ani and
Yang, Diyi and
Xiao, Ziang",
booktitle = "Proceedings of the Third Workshop on Bridging Human--Computer Interaction and Natural Language Processing",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.hcinlp-1.2",
pages = "13--27",
abstract = "The self-rationalising capabilities of large language models (LLMs) have been explored in restricted settings, using task-specific data sets.However, current LLMs do not (only) rely on specifically annotated data; nonetheless, they frequently explain their outputs.The properties of the generated explanations are influenced by the pre-training corpus and by the target data used for instruction fine-tuning.As the pre-training corpus includes a large amount of human-written explanations {``}in the wild{''}, we hypothesise that LLMs adopt common properties of human explanations.By analysing the outputs for a multi-domain instruction fine-tuning data set, we find that generated explanations show selectivity and contain illustrative elements, but less frequently are subjective or misleading.We discuss reasons and consequences of the properties{'} presence or absence. In particular, we outline positive and negative implications depending on the goals and user groups of the self-rationalising system.",
}
Markdown (Informal)
[Properties and Challenges of LLM-Generated Explanations](https://aclanthology.org/2024.hcinlp-1.2) (Kunz & Kuhlmann, HCINLP-WS 2024)
ACL
- Jenny Kunz and Marco Kuhlmann. 2024. Properties and Challenges of LLM-Generated Explanations. In Proceedings of the Third Workshop on Bridging Human--Computer Interaction and Natural Language Processing, pages 13–27, Mexico City, Mexico. Association for Computational Linguistics.