← Search

Chengyin Xu

2 accepted papers

2026

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective

ICLR 2026poster

The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for efficient resource allocation. This is challenged by: 1) the emergence phenomenon, where unpredictable capabilities appearing suddenly at critical mo…

Cited by 0SourceScholar
2023

LET: Leveraging Error Type Information for Grammatical Error Correction

ACL 2023findings

Grammatical error correction (GEC) aims to correct errors in given sentences and is significant to many downstream natural language understanding tasks. Recent work introduces the idea of grammatical error detection (GED) to improve the GEC task performance. In contrast, these explicit multi-stage w…