Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
12-2023
Abstract
Topic Modelling is an established research area where the quality of a given topic is measured using coherence metrics. Often, we infer topics from Neural Topic Models (NTM) by interpreting their decoder weights, consisting of top-activated words projected from individual neurons. Transformer-based Language Models (TLM) similarly consist of decoder weights. However, due to its hypothesised superposition properties, the final logits originating from the residual path are considered uninterpretable. Therefore, we posit that we can interpret TLM as superposed NTM by proposing a novel weight-based, model-agnostic and corpus-agnostic approach to search and disentangle decoder-only TLM, potentially mapping individual neurons to multiple coherent topics. Our results show that it is empirically feasible to disentangle coherent topics from GPT-2 models using the Wikipedia corpus. We validate this approach for GPT-2 models using Zero-Shot Topic Modelling. Finally, we extend the proposed approach to disentangle and analyse LLaMA models.
Discipline
Databases and Information Systems | Programming Languages and Compilers
Research Areas
Data Science and Engineering
Publication
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, December 6-10
First Page
8646
Last Page
8666
Publisher
ACL
City or Country
Singapore
Citation
LIM, Jia Peng and LAUW, Hady Wirawan.
Disentangling transformer language models as superposed topic models. (2023). Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, December 6-10. 8646-8666.
Available at: https://ink.library.smu.edu.sg/sis_research/8470
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://aclanthology.org/2023.emnlp-main.534