Chatbot is Not All You Need: Information-rich Prompting for More Realistic Responses
This work addresses the need for more natural and realistic reactions in conversational AI, particularly for applications involving fictional characters, but it appears incremental as it builds on existing LLM methods by adding more detailed prompting.
The paper tackles the problem of generating realistic and consistent responses from Large Language Models in conversational settings by incorporating richer information about the agent, such as senses, attributes, emotions, relationships, and memories. The result is a new benchmark dataset and released code, with the aim of improving LLM capabilities in mimicking fictional characters.
Recent Large Language Models (LLMs) have shown remarkable capabilities in mimicking fictional characters or real humans in conversational settings. However, the realism and consistency of these responses can be further enhanced by providing richer information of the agent being mimicked. In this paper, we propose a novel approach to generate more realistic and consistent responses from LLMs, leveraging five senses, attributes, emotional states, relationship with the interlocutor, and memories. By incorporating these factors, we aim to increase the LLM's capacity for generating natural and realistic reactions in conversational exchanges. Through our research, we expect to contribute to the development of LLMs that demonstrate improved capabilities in mimicking fictional characters. We release a new benchmark dataset and all our codes, prompts, and sample results on our Github: https://github.com/srafsasm/InfoRichBot