Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA (2024 · 71 citations)
Most current long-context benchmarks make inputs longer by padding them with unrelated filler text. In those setups, the evidence for an answer usually sits in one place, so a model can skip most of the input and still answer correctly. Wang et al. address this with Loong, a multi-document QA benchmark where every…
One-Shot Learning as Instruction Data Prospector for Large Language Models (2024 · 61 citations)
Instruction tuning datasets keep growing, but larger collections often carry noisy examples, and choosing good subsets usually depends on costly trial-and-error.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAConference on Empirical Methods in Natural Language Processing (EMNLP)Minzheng Wang, Longze Chen, Fu Cheng, et al.2024 · 71 citations
One-Shot Learning as Instruction Data Prospector for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Yunshui Li, Binyuan Hui, Xiaobo Xia, et al.2024 · 61 citations
GATEAU: Selecting Influential Samples for Long Context AlignmentProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · original ↗ · no summary yetShuzheng Si et al.2025 · 5 citations

Co-authors here

10 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 172 times (of the 141,840 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated 24 October 2026