UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large Models (2025 · 14 citations)
Fully fine-tuning large models is expensive in compute and in storage for per-task checkpoints. LoRA lowers this cost by training low-rank matrices. VeRA goes further: it freezes random projection matrices and trains only two scaling vectors, but it needs a high rank to stay competitive, which raises computation. The…
Advancing Arabic Sentiment Analysis: ArSen Benchmark and the Improved Fuzzy Deep Hybrid Network (2024 · 4 citations)
Arabic sentiment analysis has few resources, and the common benchmarks (Gold Standard, SemEval) are old and contain fewer than 10,000 items.
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection (2026 · 2 citations)
Benchmarks for fake news detection are mostly fixed snapshots. LLMs may have absorbed them during pre-training (benchmark data contamination, BDC), and they usually hand the model all the evidence at once, which does not match how verification works as a story is still unfolding. LiveFact addresses this with a…

All works

5 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

Benchmark Data Contamination of Large Language Models: A Survey ↗arXiv:2406.04244 · no summary yetCheng Xu et al.2024 · 85 citations
UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xueyan Zhang, Jinman Zhao, Zhifei Yang, et al.2025 · 14 citations
Advancing Arabic Sentiment Analysis: ArSen Benchmark and the Improved Fuzzy Deep Hybrid NetworkConference on Computational Natural Language Learning (CoNLL)Yang Fang, Cheng Xu, Shuhao Guan, et al.2024 · 4 citations
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News DetectionAnnual Meeting of the Association for Computational Linguistics (ACL)Cheng Xu, Changhong Jin, Yingjie Niu, et al.2026 · 2 citations
CLEAR: A Framework Enabling Large Language Models to Discern Confusing Legal Paragraphs ↗Findings of the Association for Computational Linguistics: EMNLP 2025 · no summary yetQi Xu et al.2025 · 2 citations

Co-authors here

8 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 78 times (of the 149,439 papers whose bibliographies we read); 16 citing papers with a page here →.

Updated 1 November 2026