Tag
This paper presents Structure-Guided Entity Resolution (SGER), a framework that fine-tunes LLMs through curriculum learning for robust person name matching in linguistically diverse contexts, achieving 99.02% accuracy on Indian identity data and deployed at Dream11.
A personal project led to an ACL 2026 paper introducing TIME, a method training Qwen3 models to engage in short, context-triggered thinking rather than excessive reasoning. The work uses QLoRA and a four-phase curriculum, with all data and code released open-source.