Google DeepMind 发布 CALLIOPE：用 LLM 关键词建主题树，隐私保护下优于嵌入聚类
DeepMind 新论文 CALLIOPE，让 LLM 用关键词代替嵌入做隐私话题分析，严格隐私下人类偏好率 76% 对 URANIA 的 18%。
Google DeepMind 的论文 CALLIOPE 让 LLM 为每篇文档标注少量关键词，加噪后只保留高频关键词，再由 LLM 提出主题并归类文档。传统方法对嵌入向量加噪聚类，在最严格隐私设置下得到的簇少且命名差。人类评估者在全部 3 个数据集上更偏好 CALLIOPE，而非基于嵌入的 URANIA，偏好率最高达 76% 对 18%。代价是 token 消耗为原方法的 2 到 5 倍。
New Google DeepMind paper finds that having an LLM build topic trees from keywords, not embeddings, gives clearer topic maps under strict privacy.
Teams want to know what users ask chatbots without exposing anyone. The usual private approach clusters embeddings with added noise, and under strict privacy it returns too few clusters with weak names.
CALLIOPE has an LLM tag each document with a few keywords and adds noise so only common keywords survive. The LLM then proposes topics from them and sorts documents into those topics.
At the strictest privacy setting tested, human raters preferred CALLIOPE over the embedding-based URANIA on all 3 datasets, by up to 76% versus 18%.
The method uses 2 to 5 times more tokens. For privacy-safe usage reports, start with LLM-built topics and budget for that cost.
