{"id":1057020,"date":"2024-08-05T09:00:00","date_gmt":"2024-08-05T16:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/geneva-uses-large-language-models-for-interactive-game-narrative-design\/"},"modified":"2024-07-22T09:53:21","modified_gmt":"2024-07-22T16:53:21","slug":"geneva-uses-large-language-models-for-interactive-game-narrative-design","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/research\/blog\/geneva-uses-large-language-models-for-interactive-game-narrative-design\/","title":{"rendered":"GENEVA uses large language models for interactive game narrative design"},"content":{"rendered":"\n

This paper was presented at the <\/em><\/strong>IEEE 2024 Conference on Games<\/em><\/strong> (opens in new tab)<\/span><\/a> (IEEE CoG 2024), the leading forum on innovation in and through games.<\/em><\/strong><\/p>\n\n\n\n

\"IEEE<\/figure>\n\n\n\n

Mastering the art of storytelling, a highly valued skill across films, novels, games, and more, requires creating rich narratives with compelling plots and characters. In recent years, the rise of AI has prompted inquiries into whether large language models (LLMs) can effectively generate and sustain detailed, coherent storylines that engage audiences. Consequentially, researchers have been actively exploring AI’s potential to support creative processes in video game development, where the growing demands of narrative design often surpass the capabilities of traditional tools. This investigation focuses on AI’s capacity for innovation in storytelling and the necessary human interactions to drive such advances.<\/p>\n\n\n\n

In this context, we introduce \u201cGENEVA: GENErating and Visualizing branching narratives using LLMs (opens in new tab)<\/span><\/a>,\u201d presented at IEEE CoG 2024. This graph-based narrative generation and visualization tool requires a high-level narrative description and constraints, such as the number of different starts, endings, and storylines, as well as context for grounding the narrative. GENEVA uses the generative capabilities of GPT-4 to create narratives with branching storylines and renders them in a graph format, allowing users to interactively explore different narrative paths through its web interface (opens in new tab)<\/span><\/a>.<\/p>\n\n\n\n

Visualizing narratives using graphs<\/h2>\n\n\n\n

The narrative graph itself is a directed acyclic graph (DAG), where each node represents a narrative beat<\/em>\u2014an event that moves the plot forward\u2014with directed edges (arrows) marking the progression through the story\u2019s events. These beats are the fundamental units of the narrative structure, representing the exchange of action and reaction. A single path from a start node to an end node outlines a unique storyline, and the graph illustrates the various potential storylines based on the same overarching narrative.\u202f<\/p>\n\n\n\n

The generation and visualization of these narrative graphs are accomplished using GPT-4 in a two-step process. First, the model generates the branching storylines from the given description and constraints. Second, it produces code to render these narratives in a visually comprehensible graph format.<\/p>\n\n\n\n

We detail this methodology in our paper<\/a>, through a case study where we used GENEVA to construct narrative graphs for four well-known stories\u2014Dracula<\/em>, Frankenstein<\/em>, Jack and the Beanstalk<\/em>, and Little Red Riding Hood<\/em>. Each was set in one of four distinct worlds: the game of Minecraft, the 21st<\/sup> century, ancient Rome, and the quantum realm. Figure 1 shows a narrative graph of Frankenstein set in the 21st<\/sup> century, and Figure 2 shows the storylines generated for this story.<\/p>\n\n\n\n

\"Figure
Figure 1: A narrative graph for the novel, Frankenstein, grounded in the 21st century. Additional constraints on the graph include one start, two endings, and four storylines.<\/figcaption><\/figure>\n\n\n\n
\"Figure
Figure 2: A detailed view of the four different storylines in the narrative graph in Figure 1.<\/figcaption><\/figure>\n\n\n\n\t
\n\t\t\n\n\t\t

\n\t\tSpotlight: Blog post<\/span>\n\t<\/p>\n\t\n\t

\n\t\t\t\t\t\t
\n\t\t\t\t\n\t\t\t\t\t\"MedFuzz\n\t\t\t\t<\/a>\n\t\t\t<\/div>\n\t\t\t\n\t\t\t
\n\n\t\t\t\t\t\t\t\t\t

MedFuzz: Exploring the robustness of LLMs on medical challenge problems<\/h2>\n\t\t\t\t\n\t\t\t\t\t\t\t\t

Medfuzz tests LLMs by breaking benchmark assumptions, exposing vulnerabilities to bolster real-world accuracy.<\/p>\n\t\t\t\t\n\t\t\t\t\t\t\t\t

\n\t\t\t\t\t
\n\t\t\t\t\t\t\n\t\t\t\t\t\t\tRead more\t\t\t\t\t\t<\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t<\/div>\n\t<\/div>\n\t<\/div>\n\t\n\n\n

Assessing GENEVA\u2019s narrative adaptations<\/h2>\n\n\n\n

In our assessment, we found that GENEVA performed better in specific narrative contexts. For example, in Frankenstein\u2019s<\/em> adaptation to the 21st century, the storylines included themes like creating life from DNA fragments and genetic engineering, maintaining relevance while preserving the original story\u2019s essence. However, upon closer examination, we noted areas for improvement, such as the need for more variety and better grounding of the narrative. Generally, stories that are better known and more thoroughly documented tend to yield richer and more varied adaptations.<\/p>\n\n\n\n

Implications and looking forward<\/h2>\n\n\n\n

GENEVA remains a prototype, serving as a tool for exploring the narrative capabilities of LLMs. As these models evolve, we anticipate corresponding advances in their narrative generation abilities. The ultimate goal in game design is to engage players with compelling interactive experiences. With the skilled input of experienced game designers, tools like GENEVA could increasingly contribute to creating engaging gameplay experiences through iterative refinement of narrative paths.<\/p>\n\n\n\n

Our collaboration with Xbox and Inworld AI (opens in new tab)<\/span><\/a> continues to advance the use of AI in game development, incorporating these developments into practical tools for creators. Discover more about this transformative technology by watching this video (opens in new tab)<\/span><\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"

Designed for interactive storytelling in games, GENEVA lets users explore narrative paths and adapt stories to diverse contexts. It uses LLMs to generate and visualize branching narratives from high-level descriptions, representing them as graphs.<\/p>\n","protected":false},"author":42735,"featured_media":1057038,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"categories":[1],"tags":[],"research-area":[13556],"msr-region":[],"msr-event-type":[],"msr-locale":[268875],"msr-post-option":[243984],"msr-impact-theme":[],"msr-promo-type":[],"msr-podcast-series":[],"class_list":["post-1057020","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research-blog","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-post-option-blog-homepage-featured"],"msr_event_details":{"start":"","end":"","location":""},"podcast_url":"","podcast_episode":"","msr_research_lab":[],"msr_impact_theme":[],"related-publications":[],"related-downloads":[],"related-videos":[],"related-academic-programs":[],"related-groups":[144736],"related-projects":[],"related-events":[],"related-researchers":[{"type":"user_nicename","value":"Sudha Rao","user_id":38341,"display_name":"Sudha Rao","author_link":"Sudha Rao<\/a>","is_active":false,"last_first":"Rao, Sudha","people_section":0,"alias":"sudhra"},{"type":"user_nicename","value":"Chris Brockett","user_id":31423,"display_name":"Chris Brockett","author_link":"Chris Brockett<\/a>","is_active":false,"last_first":"Brockett, Chris","people_section":0,"alias":"chrisbkt"},{"type":"user_nicename","value":"Bill Dolan","user_id":31229,"display_name":"Bill Dolan","author_link":"Bill Dolan<\/a>","is_active":false,"last_first":"Dolan, Bill","people_section":0,"alias":"billdol"}],"msr_type":"Post","featured_image_thumbnail":"\"IEEE","byline":"Sudha Rao<\/a>, Chris Brockett<\/a>, and Bill Dolan<\/a>","formattedDate":"August 5, 2024","formattedExcerpt":"Designed for interactive storytelling in games, GENEVA lets users explore narrative paths and adapt stories to diverse contexts. It uses LLMs to generate and visualize branching narratives from high-level descriptions, representing them as graphs.","locale":{"slug":"en_us","name":"English","native":"","english":"English"},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/1057020"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/users\/42735"}],"replies":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/comments?post=1057020"}],"version-history":[{"count":18,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/1057020\/revisions"}],"predecessor-version":[{"id":1059144,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/posts\/1057020\/revisions\/1059144"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/1057038"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1057020"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/categories?post=1057020"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/tags?post=1057020"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1057020"},{"taxonomy":"msr-region","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-region?post=1057020"},{"taxonomy":"msr-event-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-event-type?post=1057020"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1057020"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1057020"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1057020"},{"taxonomy":"msr-promo-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-promo-type?post=1057020"},{"taxonomy":"msr-podcast-series","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-podcast-series?post=1057020"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}