Google DeepMind 新论文提出 CALLIOPE，让 LLM 为每篇文档打上少量关键词并加噪，只保留高频关键词，再由 LLM 据此提出主题并归类文档，从而在严格隐私约束下生成更清晰的主题图。在最严格的隐私设置下，人类评审在全部 3 个数据集上都更偏好 CALLIOPE 而非基于嵌入向量的 URANIA，最高比例为 76% 对 18%。该方法消耗的 token 是后者的 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.
来源：Rohan Paul · x.com