Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

NeurIPSSpotlight2025

Authors: Jiaru Zou, Yikun Ban, Zihao Li, Yunzhe Qi, Ruizhong Qiu, Ling Yang, Jingrui He
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Large language models are typically adapted to downstream tasks through supervised fine-tuning on domain-specific data…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

large language model language model fine-tuning transformer llm

← All NeurIPS 2025 Spotlight papers · Browse the whole archive