English(EN) CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing

新基准评估LLM在创意写作中的上下文敏感语码转换能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 04:00

研究人员推出了CSWBench，一个旨在评估大型语言模型（LLM）在创意写作中上下文敏感语码转换能力的新基准。该基准包含两种设置：聚焦叙事（Focused Narrative）和扩展叙事（Extended Narrative），并附带CSWEval框架，用于评估事件和整篇文本级别的语言切换。对十二个LLM的初步评估显示，它们的语码转换能力各不相同但值得注意，与一般的叙事质量相比，模型在多语言文学整合方面表现出特别的困难。 AI

影响该基准有望促使对多语言LLM能力进行更细致的评估，从而推动用于创意和跨文化内容生成的模型改进。

排序理由该集群描述了一篇介绍用于评估LLM能力的基准的新学术论文。[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 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍用于评估LLM能力的基准的新学术论文。[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, other; 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]

arXiv cs.CL TIER_1 English(EN) · Zewen Jiang, Yahan Li, Chenlu Guo, Diana Inkpen, Yuan Wu, Yi Chang · 2026-10-15 04:00

CSWBench：评估创意写作中的上下文敏感代码切换

arXiv:2610.20272v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated multilingual capabilities across diverse language generation and understanding tasks. Yet effective code-switching requires more than multilingual proficiency: models must decide when, …

本文如何被排名

报道来源 [1]

CSWBench：评估创意写作中的上下文敏感代码切换

相关实体

相关话题