论文前沿WMT 2026QLoRA多语言摘要问答系统Tiny Aya1A 学习等级

[论文] PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering

来源:arXiv AI 论文收录:2026/8/24

✦ AI 解读

本文介绍了PSK团队在WMT 2026多语言指令共享任务中的提交系统。该系统基于3.35B参数的Tiny Aya Global模型,为每个任务训练了三个QLoRA适配器,分别用于多语言摘要、基于段落的问答和过滤后的独立问答。实验表明,在保留集上,上下文和摘要适配器优于多任务适配器,而开放问答结果因答案长度和评估方法而异。最终提交了三个系统,共享上下文和摘要适配器,但使用不同的开放问答适配器。

We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task. Our system uses the 3.35B-parameter Tiny Aya Global model with three QLoRA adapters, one for each task. The adapters are trained on multilingual document-summary pairs, passage-based question answering, and filtered standalone question answering. The summarization data also includes scientific papers with their author-written abstracts. On our held-out split, the context and summarization adapters perform better than our multitask adapter, which was trained only on data supplied by the organizers. Results for open QA are mixed and vary with answer length and evaluation method. We therefore submit three systems with the same context and summarization adapters but different open-QA adapters.
查看原文 ↗

相关推荐

Risk of transmission of amyloid β pathology via transfused blood products
✦ AI 摘要该研究探讨了通过输血传播淀粉样β病理的风险,发表于《柳叶刀》。研究可能涉及朊病毒样传播机制,对血液制品安全性和阿尔茨海默病预防有重要启示。内容来自顶级医学期刊,但属于医学领域,与AI从业者直接关联较低。
NanoGPT Speedrun Frontier
✦ AI 摘要Prime Intellect发布NanoGPT Speedrun Frontier,展示在单台GPU上以极低成本训练GPT-2级别模型的优化技术。文章详细介绍了训练速度提升的多种策略,包括数据加载、混合精度、内核优化等,并提供了可复现的代码。该研究对资源有限的AI开发者具有重要参考价值,引发社区广泛讨论。
[论文] TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems
✦ AI 摘要TurboBias 2.0 是一个面向生产环境的 ASR 系统上下文偏置框架,旨在解决流式推理、批量解码、用户特定上下文列表和低运行时开销等实际需求。它扩展了 GPU 加速的 TurboBias,引入不区分大小写的提升图和每流批量解码,使批次中的每个话语都能使用独立的上下文配置,从而实现个性化上下文处理,提升识别准确率并保持高效。