LLM伦理对齐与拒绝回答对用户满意度的影响分析，基于50,000次模型对比实验，区分伦理和技术拒绝原因，发现伦理拒绝导致显著更高的用户不满（拒绝惩罚），但敏感上下文和详细回应可缓解负面影响，揭示安全行为与用户期望的冲突。 摘要 大语言模型（LLM ...

Langdock GmbH, a startup with an enterprise chatbot that allows users to change the underlying language model, has raised $3 million in seed funding to support its growth efforts. TechCrunch reported ...

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot ‘Amanda’ for relationship support shows that a single session of chatbot therapy can ...

In long conversations, chatbots generate large “conversation memories” (KV). KVzip selectively retains only the information useful for any future question, autonomously verifying and compressing its ...