llm-conversations

CALLIOPE 是一个支持差分隐私的自顶向下主题层级发现框架，直接利用 LLM 能力处理大规模非结构化语料（如 LLM 对话），无需依赖向量嵌入聚类，在高隐私预算约束下优于现有基于嵌入的方法。

The paper studies how users seek legal guidance in real-world LLM conversations, introducing a taxonomy, annotating 2,122 WildChat conversations, and releasing a 200-conversation evaluation set along with trained classifiers and public resources.

This paper introduces Grounded Continuation, a linear-time runtime verifier for LLM conversations that maintains an explicit dependency graph to detect whether a next utterance is supported by prior conversation, achieving accuracy gains over baselines on benchmarks including LongMemEval and LoCoMo.