An official website of the United States government
Creating engaging interactive story-based experiences dynamically responding to individual player choices poses significant challenges for narrative-centered games. Recent advances in pre-trained large language models (LLMs) have the potential to revolutionize procedural content generation for narrative-centered games. Historically, interactive narrative generation has specified pivotal events in the storyline, often utilizing planning-based approaches toward achieving narrative coherence and maintaining the story arc. However, manual authorship is typically used to create detail and variety in non-player character (NPC) interaction to specify and instantiate plot events. This paper proposes SCENECRAFT, a narrative scene generation framework that automates NPC interaction crucial to unfolding plot events. SCENECRAFT interprets natural language instructions about scene objectives, NPC traits, location, and narrative variations. It then employs large language models to generate game scenes aligned with authorial intent. It generates branching conversation paths that adapt to player choices while adhering to the author’s interaction goals. LLMs generate interaction scripts, semantically extract character emotions and gestures to align with the script, and convert dialogues into a game scripting language. The generated script can then be played utilizing an existing narrative-centered game framework. Through empirical evaluation using automated and human assessments, we demonstrate SCENECRAFT’s effectiveness in creating narrative experiences based on creativity, adaptability, and alignment with intended author instructions.
more »
« less
Solution Density and Search Strategy in Narrative Generation
Intelligent interactive narrative systems coordinate a cast of non-player characters to make the overall story experience meaningful for the player. Narrative generation involves a tradeoff between plot-structure requirements and quality of character behavior, as well as computational efficiency. We study this tradeoff using the example of benchmark problems for narrative planning algorithms. A typical narrative planning problem calls for a sequence of actions that leads to an overall plot goal being met, while also requiring each action to respect constraints that create the appearance of character autonomy. We consider simplified solution definitions that enforce only plot requirements or only character requirements, and we measure how often each of these definitions leads to a solution that happens to meet both types of requirements—i.e., the density with which narrative plans occur among plot- or character-requirement-satisfying sequences. We then investigate whether solution densities can guide the selection of narrative planning algorithms. We compare the performance of two search strategies: one that satisfies plot requirements first and checks character requirements afterward, and one that continuously verifies character requirements. Our results show that comparing solution densities does not by itself predict which of these search strategies will be more efficient in terms of search nodes visited, suggesting that other important factors exist. We discuss what some of these factors could be. Our work opens further investigation into characterizing narrative planning algorithms and how they interact with specific domains. The results also highlight the diversity and difficulty of solving narrative planning problems.
more »
« less
- Award ID(s):
- 1911053
- PAR ID:
- 10375771
- Date Published:
- Journal Name:
- IEEE Transactions on Games
- ISSN:
- 2475-1502
- Page Range / eLocation ID:
- 1 to 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)One of the most fundamental elements of narrative is character: if we are to understand a narrative, we must be able to identify the characters of that narrative. Therefore, character identification is a critical task in narrative natural language understanding. Most prior work has lacked a narratologically grounded definition of character, instead relying on simplified or implicit definitions that do not capture essential distinctions between characters and other referents in narratives. In prior work we proposed a preliminary definition of character that was based in clear narratological principles: a character is an animate entity that is important to the plot. Here we flesh out this concept, demonstrate that it can be reliably annotated (0.78 Cohen’s κ), and provide annotations of 170 narrative texts, drawn from 3 different corpora, containing 1,347 character co-reference chains and 21,999 non-character chains that include 3,937 animate chains. Furthermore, we have shown that a supervised classifier using a simple set of easily computable features can effectively identify these characters (overall F1 of 0.90). A detailed error analysis shows that character identification is first and foremost affected by co-reference quality, and further, that the shorter a chain is the harder it is to effectively identify as a character. We release our code and data for the benefit of other researchersmore » « less
-
Narrative generation systems can be classified on a spectrum from strong autonomy to strong story. Systems on the strong autonomy side treat characters as fully independent agents but may struggle to meet the author’s requirements, while those on the strong story side direct character behaviors centrally but may struggle to create the illusion of character believability. In this paper, we use benchmark story generation problems as a framework to compare the spaces of stories that could be generated by prototypical strong story and strong autonomy systems. Comparing the relative solution densities of these spaces helps us quantify how common certain desirable narrative properties are. This can be informative for system designers when deciding, for instance, whether to strictly enforce all desired properties or to generate and filter from a broader class of solutions.more » « less
-
Narrative planning is the process of generating sequences of actions that form coherent and goal-oriented narratives. Classical implementations of narrative planning rely on heuristic search techniques to offer structured story generation but face challenges with scalability due to large branching factors and deep search requirements. Large Language Models (LLMs), with their extensive training on diverse linguistic datasets, excel in understanding and generating coherent narratives. However, their planning ability lacks the precision and structure needed for effective narrative planning. This paper explores a hybrid approach that uses LLMs as heuristic guides within classical search frameworks for narrative planning. We compare various prompt designs to generate LLM heuristic predictions and evaluate their performance against h+, hmax, and relaxed plan heuristics. Additionally, we analyze the ability of relaxed plans to predict the next action correctly, comparing it to the LLMs’ ability to make the same prediction. Our findings indicate that LLMs rarely exceed the accuracy of classical planning heuristics.more » « less
-
Characters are a key element of narrative and so character identification plays an important role in automatic narrative understanding. Unfortunately, most prior work that incorporates character identification is not built upon a clear, theoretically grounded concept of character. They either take character identification for granted (e.g., using simple heuristics on referring expressions), or rely on simplified definitions that do not capture important distinctions between characters and other referents in the story. Prior approaches have also been rather complicated, relying, for example, on predefined case bases or ontologies. In this paper we propose a narratologically grounded definition of character for discussion at the workshop, and also demonstrate a preliminary yet straightforward supervised machine learning model with a small set of features that performs well on two corpora. The most important of the two corpora is a set of 46 Russian folktales, on which the model achieves an F1 of 0.81. Error analysis suggests that features relevant to the plot will be necessary for further improvements in performance.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TG.2022.3149529
