Zero-Shot Multi-Label Topic Inference with Sentence Encoders and LLMs

Souvika Sarkar, Dongji Feng, Shubhra Kanti Karmaker Santu


Abstract
In this paper, we conducted a comprehensive study with the latest Sentence Encoders and Large Language Models (LLMs) on the challenging task of “definition-wild zero-shot topic inference”, where users define or provide the topics of interest in real-time. Through extensive experimentation on seven diverse data sets, we observed that LLMs, such as ChatGPT-3.5 and PaLM, demonstrated superior generality compared to other LLMs, e.g., BLOOM and GPT-NeoX. Furthermore, Sentence-BERT, a BERT-based classical sentence encoder, outperformed PaLM and achieved performance comparable to ChatGPT-3.5.
Anthology ID:
2023.emnlp-main.1008
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16218–16233
Language:
URL:
https://aclanthology.org/2023.emnlp-main.1008
DOI:
10.18653/v1/2023.emnlp-main.1008
Bibkey:
Cite (ACL):
Souvika Sarkar, Dongji Feng, and Shubhra Kanti Karmaker Santu. 2023. Zero-Shot Multi-Label Topic Inference with Sentence Encoders and LLMs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16218–16233, Singapore. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Multi-Label Topic Inference with Sentence Encoders and LLMs (Sarkar et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.1008.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.1008.mp4