Active Preference Inference using Language Models and Probabilistic Reasoning

arXiv:2312.12009v2 Announce Type: replace
Abstract: Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences. To enable this ability for instruction-tuned large language models (LLMs), one may prompt them to ask users questions to infer their preferences, transforming the language models into more robust, interactive systems. However, out of the box, these models are not efficient at extracting preferences: …

abstract adapt arxiv cs.ai cs.cl cs.lg decision example good human important inference instruction-tuned language language models large language large language models llms making prompt questions reasoning replace systems them type