English(EN) Gacha Decoding: Eliciting Diverse Generations Through Instruction Following

Gacha 解码方法提升语言模型生成多样性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 04:00

研究人员推出了一种新颖的推理时方法 Gacha 解码，旨在增强语言模型生成的 P 样性。该技术将多样性视为一个指令遵循问题，将模型的指令遵循能力与外部随机数生成器的随机性相结合。Gacha 解码在各种开放式领域中，相较于现有的多样性方法，均取得了显著的改进，Vendi 分数提高了 2.4 倍，并以更少的样本识别出了新颖的生成模式。 AI

影响该方法有望使语言模型的输出更加多样化和富有创意，从而增强其在创意写作和开放式聊天等任务中的实用性。

排序理由该集群包含一篇详细介绍语言模型生成新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍语言模型生成新方法的学术论文。[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.AI TIER_1 English(EN) · Scott Geng, Yufei Zhang, Joseph Lee, Jerry Li, Marjan Ghazvininejad, Pang Wei Koh · 2026-10-02 04:00

Gacha解码：通过指令遵循引发多样化生成

arXiv:2610.01382v1 Announce Type: new Abstract: We introduce Gacha Decoding, an inference-time method for eliciting diverse language model generations that scales with model capability. Across open-ended domains (in-the-wild chat, creative writing, planning for image generation, …

本文如何被排名

报道来源 [1]

Gacha解码：通过指令遵循引发多样化生成

相关实体

相关话题