Tatsuro KAWAMOTOMulti-Agent Prompts in LLMs: Do They Really Work?Attempts to improve LLM performance range from modifying model architectures to prompt engineering such as the Chain of Thoughts (CoT). In…Jul 1Jul 1
Tatsuro KAWAMOTOCan ChatGPT Detect Hate Speech?Ethical issues have been a concern since the very early stages of research on large language models (LLMs). While there have been several…Jun 17Jun 17
Tatsuro KAWAMOTOCalibration of LLM: Can You Trust The Result If The “logprob” is High?When you use OpenAI’s GPT through the API, you can get `logprobs` for each token in the output, which stands for log-probabilities. In…Jun 10Jun 10
Tatsuro KAWAMOTOWhat is MMLU? Measuring the performance of LLMsThere are many benchmark datasets for LLMs. This time, I summarize the dataset MMLU (Massive Multitask Language Understanding) introduced…Jun 6Jun 6
Tatsuro KAWAMOTOParallel Coordinate Plot Explained (3/3)In the previous post, I explained the point-line duality in Parallel Coordinate Plots.May 23May 23
Tatsuro KAWAMOTOParallel Coordinate Plot Explained (2/3)In the previous post, we considered a table of data as the input.May 21May 21
Tatsuro KAWAMOTOParallel Coordinate Plot Explained (1/3)The Parallel Coordinate Plot is, in short, a method to visualize high-dimensional data on a two-dimensional plane, as shown below.May 20May 20
Tatsuro KAWAMOTOHierarchical Edge Bundling Explained (3/3)In this post, I will go over the related works of hierarchical edge bundling mentioned in D. Holten’s 2006 paper.May 21May 21
Tatsuro KAWAMOTOHierarchical Edge Bundling Explained (2/3)In the previous post, I explained how to interpret the hierarchical edge bundling and how it is drawn, following the original paper by D…Apr 25Apr 25
Tatsuro KAWAMOTOHierarchical Edge Bundling Explained (1/3)If you want to learn about the hierarchical edge bundling (or hierarchical edge bundles) in detail, you are on the right post. I basically…Apr 23Apr 23