LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversational History

arXiv:2402.18216v1 Announce Type: new
Abstract: With the recent emergence of powerful instruction-tuned large language models (LLMs), various helpful conversational Artificial Intelligence (AI) systems have been deployed across many applications. When prompted by users, these AI systems successfully perform a wide range of tasks as part of a conversation. To provide some sort of memory and context, such approaches typically condition their output on the entire conversational history. Although this sensitivity to the conversational history can often lead to improved performance …

abstract ai systems applications artificial artificial intelligence arxiv conversational conversational artificial intelligence cs.cl emergence history impact instruction-tuned intelligence interference language language models large language large language models llm llms part study systems tasks type