Robust Knowledge Extraction from Large Language Models using Social Choice Theory

Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking …

agents applications conversational conversational agents creative cs.ai cs.cl domains extraction general knowledge language language models large language large language models llms medicine query robust social support theory writing