← Search

Jinxiang Xie

2 accepted papers

2025

DSGram: Dynamic Weighting Sub-Metrics for Grammatical Error Correction in the Era of Large Language Models

AAAI 2025technical

Evaluating the performance of Grammatical Error Correction (GEC) models has become increasingly challenging, as large language model (LLM)-based GEC systems often produce corrections that diverge from provided gold references. This discrepancy undermines the reliability of traditional reference-base…

2025

GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking

ACL 2025long

Large language models (LLMs) are widely used, but they often generate subtle factual errors, especially in long-form text. These errors are fatal in some specialized domains such as medicine. Existing fact-checking with grounding documents methods face two main challenges: (1) they struggle to under…