Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting (2024 · 300 citations)
The paper addresses why off-the-shelf LLMs have struggled to rank documents for a query as well as fine-tuned rankers.
LiPO: Listwise Preference Optimization through Learning-to-Rank (2025 · 31 citations)
Most alignment methods that skip full RLHF, such as DPO and SLiC, learn only from pairs of responses. Human or reward-model feedback, however, often ranks several responses to the same prompt. The authors treat alignment as a Learning-to-Rank (LTR) problem. The prompt plays the role of a query, the sampled responses…
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026 · 1 citation)
Mainstream LLMs are trained mostly on high-resource languages, so Tibetan remains poorly served despite its millions of speakers and cultural importance. The authors build an end-to-end pipeline to close this gap.

All works

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

DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetOrest Kupyn et al.2019 · 1,165 citations
Large Language Models are Effective Text Rankers with Pairwise Ranking PromptingFindings of the Association for Computational LinguisticsZhen Qin, Rolf Jagerman, Kai Hui, et al.2024 · 300 citations
LiPO: Listwise Preference Optimization through Learning-to-RankConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Tianqi Liu, Zhen Qin, Junru Wu, et al.2025 · 31 citations
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for TibetanAnnual Meeting of the Association for Computational Linguistics (ACL)Lei Yang, Leiyu Pan, Bojian Xiong, et al.2026 · 1 citation

Co-authors here

12 of 22 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 188 times (of the 149,439 papers whose bibliographies we read); 30 citing papers with a page here →.

Updated 1 November 2026