English(EN) Evaluating Whether LLMs Can Reliably Connect the DOTs?

Gemma-2-2B 在叙事填空基准测试中表现优于更大的大型语言模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-01 04:00

引入了一个新的叙事填空基准测试，旨在评估大型语言模型（LLMs）在故事中重建缺失句子的能力。该基准测试包含四种叙事类型，约9.2K个实例，用于测试20个开源LLMs。出人意料的是，模型规模与性能不相关；Gemma-2-2B 获得了最高的定性分数，超越了 DeepSeek-Qwen-32B 和 LLaMA-3.3-70B 等更大的模型。明确的推理技术仅提供了边际改进，表明叙事特征和长度是当前LLMs任务难度的更重要因素。 AI

影响这项研究强调，更小、更高效的模型可以在复杂任务上取得卓越的性能，这可能会影响未来LLM的开发和部署策略。

排序理由该集群描述了一篇介绍用于评估LLM能力的新基准测试的学术论文。[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: 21 / 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能力的新基准测试的学术论文。[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, 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]

arXiv cs.CL TIER_1 English(EN) · Eftekhar Hossain, John Salvador, Santu Karmaker · 2026-10-01 04:00

评估大型语言模型是否能可靠地连接DOTS？

arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct missing spans within a broader storyline, commonly referred to as text infilling, w…

本文如何被排名

报道来源 [1]

评估大型语言模型是否能可靠地连接DOTS？

相关实体

相关话题