PulseAugur
中
实时 08:52:41
English(EN) Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation

新框架检测僧伽罗语到英语机器翻译中的幻觉

研究人员开发了一个新颖的框架来检测僧伽罗语到英语神经机器翻译中的病理性幻觉。该系统利用了一个包含 45,000 个样本的合成数据集,该数据集是通过五种损坏策略和一种语义救援机制创建的。微调后的 mDeBERTa-v3 模型在 token 级别达到了 0.841 的 F1 分数,并且通过神经风险分数、序列对数概率和跨语言嵌入的集成进一步提高了检测准确率,AUROC 达到了 0.970。研究还揭示了八种不同 NMT 系统在幻觉率方面存在显著差异。 AI

影响 通过改进翻译错误的检测和缓解,这项研究可能有助于开发更可靠的机器翻译系统,特别是对于低资源语言。

排序理由 该集群包含一篇学术论文,详细介绍了机器翻译中幻觉检测的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新框架检测僧伽罗语到英语机器翻译中的幻觉

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇学术论文,详细介绍了机器翻译中幻觉检测的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Navam Obeysekara, Nevidu Jayatilleke ·

    事实胜于雄辩:检测僧伽罗语到英语神经机器翻译中的病理性幻觉

    arXiv:2610.11389v1 Announce Type: new Abstract: Neural Machine Translation (NMT) models, while capable of producing highly fluent outputs, remain vulnerable to hallucinations, which are translations that are natural yet semantically unrelated to the source. This vulnerability is …