Style Locality for Controllable Generation with kNN Language Models

Gilles Nawezi, Lucie Flek, Charles Welch


Abstract
Recent language models have been improved by the addition of external memory. Nearest neighbor language models retrieve similar contexts to assist in word prediction. The addition of locality levels allows a model to learn how to weight neighbors based on their relative location to the current text in source documents, and have been shown to further improve model performance. Nearest neighbor models have been explored for controllable generation but have not examined the use of locality levels. We present a novel approach for this purpose and evaluate it using automatic and human evaluation on politeness, formality, supportiveness, and toxicity textual data. We find that our model is successfully able to control style and provides a better fluency-style trade-off than previous work
Anthology ID:
2023.tllm-1.7
Volume:
Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants!
Month:
September
Year:
2023
Address:
Prague, Czech Republic
Editors:
Devamanyu Hazarika, Xiangru Robert Tang, Di Jin
Venues:
TLLM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
68–75
Language:
URL:
https://aclanthology.org/2023.tllm-1.7
DOI:
Bibkey:
Cite (ACL):
Gilles Nawezi, Lucie Flek, and Charles Welch. 2023. Style Locality for Controllable Generation with kNN Language Models. In Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants!, pages 68–75, Prague, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
Style Locality for Controllable Generation with kNN Language Models (Nawezi et al., TLLM-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.tllm-1.7.pdf