Kaggle Competition Report: Automated Essay Scoring 2.0
July 07, 2024 | 5 min readThis competition was all about distribution shift. Let's learn how the winners conquered the challenge.
![[object Object]](/static/2d0f4e01d6e61412b3e92139e5695299/d8057/profile-pic.webp)
Aligning LLMs without Paired Preference Labels
May 08, 2024 | 3 min readIt's hard to collect paired preferences. Can we align LLMs without them? Yes, with KTO!
Aligning LLMs without Reinforcement Learning
April 27, 2024 | 3 min readDPO reduces the effort required to align LLMs. Here is how I created the Reviewer #2 Bot from TinyLlama using DPO.
Elo vs Bradley-Terry: Which is Better for Comparing the Performance of LLMs?
March 17, 2024 | 4 min readChatbot Arena updated its LLM ranking method from Elo to Bradley-Terry. What changed? Let's dig into the differences.
Unpacking the Tricky Behavior of React Navigation's navigate Function
March 09, 2024 | 2 min readDoes your React Native app go back to an unexpected screen? Here's how to deal with it.
『デュアルキャリア・カップル』を読んで夫婦で話したこと
February 03, 2024 | 6 min read『デュアルキャリア・カップル』を読んで、「第一の転換期」を乗り越えるために夫婦で話したことについて書きます。
Year in Review: Deep Learning Papers in 2023
January 27, 2024 | 12 min readLet's look back at the significant progress made in deep learning in 2023! Here are my 10 favorite papers.
Kaggle Competition Report: LLM Science Exam
November 19, 2023 | 4 min readCan LLMs answer scientific questions? See how Kaggle winners used LLMs and RAG!
Simulating Real-Time Chats using Flask's Server-Sent Events
November 06, 2023 | 2 min readDiscover the power of Flask's Server-Sent Events for better developer's experience of chatbots.
