Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Paper Summary - Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Summary of Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet.
Paper Summary: Improving Alignment and Robustness with Circuit Breakers
Summary of Improving Alignment and Robustness with Circuit Breakers.
Paper Summary - GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
Summary of Understanding the Limitations of Mathematical Reasoning in Large Language Models.
Generating Audio Files for Learning Languages
In this post, I walk you through how I generated podcasts for assisting people in language learning.
portfolio
publications
Hierarchical Text Classification using Language Models with Global Label-wise Attention Mechanisms
Published in Artificial Intelligence Research. SACAIR 2023. Communications in Computer and Information Science, vol 1976.
Recommended citation: du Toit, J., Dunaiski, M. (2023). Hierarchical Text Classification Using Language Models with Global Label-Wise Attention Mechanisms. In: Pillay, A., Jembere, E., J. Gerber, A. (eds) Artificial Intelligence Research. SACAIR 2023. Communications in Computer and Information Science, vol 1976. Springer, Cham. https://doi.org/10.1007/978-3-031-49002-6_18
Download Paper | Download Slides
Hierarchical Text Classification with Transformer-based Language Models
Published in Stellenbosch University
Recommended citation: du Toit, J. (2024). Hierarchical Text Classification with Transformer-based Language Models. https://scholar.sun.ac.za/items/0eb2b468-ca45-402b-ab23-5632230fb8d3
Download Paper | Download Slides
Prompt Tuning Discriminative Language Models for Hierarchical Text Classification
Published in Natural Language Processing
Recommended citation: du Toit, J. and Dunaiski, M. Prompt tuning discriminative language models for hierarchical text classification. Natural Language Processing https://doi.org/10.1017/nlp.2024.51
Download Paper