CALYPSO:作为地下城主助手的 LLM
CALYPSO: LLMs as Dungeon Masters' Assistants
AI总结:
本文提出 CALYPSO 系统,利用 LLM 为《龙与地下城》的地下城主提供场景信息提炼与创意头脑风暴支持,在保持 DM 创作自主权的同时实现同步创造性协助。
摘要:
在《龙与地下城》游戏中,地下城主(DM)的角色需要同时执行多项任务。DM 必须消化关于游戏设定和怪物的信息,合成场景呈现给其他玩家,并回应玩家与场景的互动。在保持叙事和故事世界一致性的同时完成所有这些任务,对人类认知而言并非易事,这使得该任务令人疲惫且对新玩家来说难以接近。像 GPT-3 和 ChatGPT 这样的大型语言模型(LLM)已展现出生成连贯自然语言文本的卓越能力。在本文中,我们与 DM 进行了一项形成性评估,以确立 LLM 在 D&D 以及更广泛的桌面游戏中的使用场景。我们介绍了 CALYPSO,一个由 LLM 驱动的界面系统,为 DM 提供针对其自身场景的信息和灵感支持。CALYPSO 将游戏上下文提炼为简短的散文,并帮助头脑风暴创意,而不会使 DM 从游戏中分心。当获得 CALYPSO 的使用权限时,DM 报告称它生成了适合直接呈现给玩家的高保真文本,以及 DM 可以在保持其创作自主权的同时进一步发展的低保真创意。我们认为 CALYPSO 体现了一种 AI 增强工具的范式,该范式在既定的游戏世界以及更广泛的桌面游戏中提供同步的创造性协助。
英文摘要:
The role of a Dungeon Master, or DM, in the game Dungeons & Dragons is to perform multiple tasks simultaneously. The DM must digest information about the game setting and monsters, synthesize scenes to present to other players, and respond to the players' interactions with the scene. Doing all of these tasks while maintaining consistency within the narrative and story world is no small feat of human cognition, making the task tiring and unapproachable to new players. Large language models (LLMs) like GPT-3 and ChatGPT have shown remarkable abilities to generate coherent natural language text. In this paper, we conduct a formative evaluation with DMs to establish the use cases of LLMs in D&D and tabletop gaming generally. We introduce CALYPSO, a system of LLM-powered interfaces that support DMs with information and inspiration specific to their own scenario. CALYPSO distills game context into bite-sized prose and helps brainstorm ideas without distracting the DM from the game. When given access to CALYPSO, DMs reported that it generated high-fidelity text suitable for direct presentation to players, and low-fidelity ideas that the DM could develop further while maintaining their creative agency. We see CALYPSO as exemplifying a paradigm of AI-augmented tools that provide synchronous creative assistance within established game worlds, and tabletop gaming more broadly.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。