Published as a conference paper at ICLR 2025R 2: A LLM B ASED N OVEL-TO-S CREENPLAYG ENER-ATIONF RAMEWORK WITH C AUSALP LOT G RAPHS Zefeng Lin 1, Yi Xiao 1, Zhiqiang Mo 1, Qifan Zhang 1, Jie Wang 2, Jiayang Chen 2, Jiajing Zhang 2, Hui Zhang 1, Zhengyi Liu 3, Xianyong Fang 3, Xiaohua Xu 1 1 University of Science and Technology of China 2 Anhui Jianzhu University 3 Anhui University A BSTRACT Automatically adapting novels into screenplays is important for the TV, film, or opera industries to promote products with low costs. The strong performances of large language models (LLMs) in long-text generation call us to propose a LLM based framework Reader-Rewriter (R 2) for this task. However, there are two fundamental challenges here. First, the LLM hallucinations may cause inconsistent plot extraction and screenplay generation. Second, the causality-embedded plot lines should be effectively extracted for coherent rewriting. Therefore, two corresponding tactics are proposed: 1) A hallucination-aware refinement method (HAR) to iteratively discover and eliminate the affections of hallucinations; and 2) a causal plot-graph construction method (CPC) based on a greedy cycle-breaking algorithm to efficiently construct plot lines with event causalities. Recruiting those efficient techniques, R 2 utilizes two modules to mimic the human screenplay rewriting process: The Reader module adopts a sliding window and CPC to build the causal plot graphs, while the Rewriter module generates first the scene outlines based on the graphs and then the screenplays. HAR is integrated into both modules for accurate inferences of LLMs.

Automated story generation is the use of an intelligent system to produce a fictional story from a minimal set of inputs. This is a problem that has long been explored by AI researchers, since it strikes at some fundamental research questions in artificial intelligence. To tell a story, an intelligent system has to have a lot of knowledge, both about how to tell a story and about how the world works. These concepts need to be grounded to be able to tell coherent stories. Story generation is therefore an excellent way to know if an intelligent system truly understands something. To understand a concept, one must be able to put that concept into practice -- telling a story in which a concept is used correctly is one way of doing that. For example, if an AI system tells a story about going to a restaurant, as simple as that sounds, we discover very quickly what the system doesn't understand when it messes up basic details. Besides understanding concepts, storytelling also requires an understanding of the listener or reader, known as a theory of mind -- a model of the listener to reason about what needs to be said or what can be left out and still convey a comprehensible story. In addition to these fundamental AI research problems, automated story generation is also worth studying for the applications it may enable. The remainder of this article will present a primer on the field of research that I think my students need to know to get started on research on automated story generation, and that anyone interested in the topic of automated story generation may find it informative. A caveat: since I have been actively researching automated story generation for nearly two decades, this primer will be somewhat biased toward work from my research group and collaborators. We might distinguish between automated story generation and automated plot generation.

Automated story plot generation is the task of generating a coherent sequence of plot events. Causal relations between plot events are believed to increase the perception of story and plot coherence. In this work, we introduce the concept of soft causal relations as causal relations inferred from commonsense reasoning. We demonstrate C2PO, an approach to narrative generation that operationalizes this concept through Causal, Commonsense Plot Ordering. Using human-participant protocols, we evaluate our system against baseline systems with different commonsense reasoning reasoning and inductive biases to determine the role of soft causal relations in perceived story quality. Through these studies we also probe the interplay of how changes in commonsense norms across storytelling genres affect perceptions of story quality.

In this paper we present the Creative Invention Benchmark (CrIB), a 2000-problem benchmark for evaluating a particular facet of computational creativity. Specifically, we address combinational p-creativity, the creativity at play when someone combines existing knowledge to achieve a solution novel to that individual.

Value alignment is a property of an intelligent agent indicating that it can only pursue goals that are beneficial to humans. Successful value alignment should ensure that an artificial general intelligence cannot intentionally or unintentionally perform behaviors that adversely affect humans. This is problematic in practice since it is difficult to exhaustively enumerated by human programmers. In order for successful value alignment, we argue that values should be learned. In this paper, we hypothesize that an artificial intelligence that can read and understand stories can learn the values tacitly held by the culture from which the stories originate.We describe preliminary work on using stories to generate a value-aligned reward signal for reinforcement learning agents that prevents psychotic-appearing behavior.

In this work, we introduce a technique that uses stories totrain virtual agents to exhibit believable behavior. This technique uses a compact representation of a story to define the space of acceptable behaviors and then uses this space to assign rewards to certain world states. We show the effectiveness of our technique with a case study in a modified gridworld environment called Pharmacy World. The results show that a reinforcement learning agent using Q-learning was able to learn a policy that results in believable behavior.

Interactive narrative is a form of storytelling in which users affect a dramatic storyline through actions by assuming the role of characters in a virtual world.This extended abstract outlines the Scheherazade-IF system, which uses crowdsourcing and artificial intelligence to automatically construct text-based interactive narrative experiences.

Story generation is the problem of automatically selecting a sequence of events that meet a set of criteria and can be told as a story. Story generation is knowledge-intensive; traditional story generators rely on a priori defined domain models about fictional worlds, including characters, places, and actions that can be performed. Manually authoring the domain models is costly and thus not scalable. We present a novel class of story generation system that can generate stories in an unknown domain. Our system (a) automatically learns a domain model by crowdsourcing a corpus of narrative examples and (b) generates stories by sampling from the space defined by the domain model. A large-scale evaluation shows that stories generated by our system for a previously unknown topic are comparable in quality to simple stories authored by untrained humans

Interactive narrative is a form of storytelling that adapts to actions performed by users who assume the roles of story characters. To date, interactive narratives are built by hand. In this paper, we introduce Scheherazade, an intelligent system that automatically creates an interactive narrative about any topic from crowdsourced narratives. Our system leverages the experience and creativity of humans by crowdsourcing a corpus of linear narrative examples. It then constructs an executable plot graph, which is a knowledge structure that defines the legal space of an interactive narrative, by learning the plot events, execution precedence, and event separations. We demonstrate the system can successfully construct an interactive narrative based on noisy human input.

Computational systems can use sociocultural knowledge to understand human behavior and interact with humans in more natural ways. However, such systems are limited by their reliance on hand-authored sociocultural knowledge and models. We introduce an approach to automatically learn robust, script-like sociocultural knowledge from crowdsourced narratives. Crowdsourcing, the use of anonymous human workers, provides an opportunity for rapidly acquir­ing a corpus of examples of situations that are highly specialized for our purpose yet sufficiently varied, from which we can learn a versatile script. We describe a semi-automated process by which we query human workers to write natural language narrative examples of a given situation and learn the set of events that can occur and the typical even ordering.