3 papers
cs.AI2026
Phantom Gains: Auditing Self-Improvement Against a Measured Null
Cheng Xu, Nan Yan, Liming Chen +1
Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses. Tracking these transitions means diffe…
cs.CL2025
DCR: Quantifying Data Contamination in LLMs Evaluation
Cheng Xu, Nan Yan, Shuhao Guan +4
The rapid advancement of large language models (LLMs) has heightened concerns about benchmark data contamination (BDC), where models inadvertently memorize evaluation data during t…
cs.CL2025
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy
Shuhao Guan, Moule Lin, Cheng Xu +5
This paper introduces PreP-OCR, a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual con…