Dialogue-based Role Playing Games (RPGs) require powerful storytelling. The
narratives of these may take years to write and typically involve a large
creative team. In this work, we demonstrate the potential of large generative
text models to assist this process. \textbf{GRIM}, a prototype
\textbf{GR}aph-based \textbf{I}nteractive narrative visualization system for
ga\textbf{M}es, generates a rich narrative graph with branching storylines that
match a high-level narrative description and constraints provided by the
designer. Game designers can interactively edit the graph by automatically
generating new sub-graphs that fit the edits within the original narrative and
constraints. We illustrate the use of \textbf{GRIM} in conjunction with GPT-4,
generating branching narratives for four well-known stories with different
contextual constraints.

在这项研究中，我们展示了大型生成文本模型辅助生成丰富的、分支故事线的图形互动叙述可用于对接具备不同上下文约束的四个著名故事，通过与 GPT-4 的配合来进行游戏设计的例证。

基于图的游戏交互叙事可视化（GRIM）

GRIM: GRaph-based Interactive narrative visualization for gaMes

The spread of online misinformation threatens public health, democracy, and
the broader society. While professional fact-checkers form the first line of
defense by fact-checking popular false claims, they do not engage directly in
conversations with misinformation spreaders. On the other hand, non-expert
ordinary users act as eyes-on-the-ground who proactively counter misinformation
-- recent research has shown that 96% counter-misinformation responses are made
by ordinary users. However, research also found that 2/3 times, these responses
are rude and lack evidence. This work seeks to create a counter-misinformation
response generation model to empower users to effectively correct
misinformation. This objective is challenging due to the absence of datasets
containing ground-truth of ideal counter-misinformation responses, and the lack
of models that can generate responses backed by communication theories. In this
work, we create two novel datasets of misinformation and counter-misinformation
response pairs from in-the-wild social media and crowdsourcing from
college-educated students. We annotate the collected data to distinguish poor
from ideal responses that are factual, polite, and refute misinformation. We
propose MisinfoCorrect, a reinforcement learning-based framework that learns to
generate counter-misinformation responses for an input misinformation post. The
model rewards the generator to increase the politeness, factuality, and
refutation attitude while retaining text fluency and relevancy. Quantitative
and qualitative evaluation shows that our model outperforms several baselines
by generating high-quality counter-responses. This work illustrates the promise
of generative text models for social good -- here, to help create a safe and
reliable information ecosystem. The code and data is accessible on
this https URL

本论文旨在通过建立一个基于强化学习的生成式文本模型 MisinfoCorrect 来有效地纠正不实信息，在社交媒体和众包数据的基础上，创造了两个新的数据集，并通过定量和定性评估证明了该模型可以生成高质量的反驳回复，提高了礼貌性，事实性和反驳态度。

基于强化学习的反误信息生成：以 COVID-19 疫苗误信息为例

Reinforcement Learning-based Counter-Misinformation Response Generation:  A Case Study of COVID-19 Vaccine Misinformation

This paper seeks to develop a deeper understanding of the fundamental
properties of neural text generations models. The study of artifacts that
emerge in machine generated text as a result of modeling choices is a nascent
research area. Previously, the extent and degree to which these artifacts
surface in generated text has not been well studied. In the spirit of better
understanding generative text models and their artifacts, we propose the new
task of distinguishing which of several variants of a given model generated a
piece of text, and we conduct an extensive suite of diagnostic tests to observe
whether modeling choices (e.g., sampling methods, top-$k$ probabilities, model
architectures, etc.) leave detectable artifacts in the text they generate. Our
key finding, which is backed by a rigorous set of experiments, is that such
artifacts are present and that different modeling choices can be inferred by
observing the generated text alone. This suggests that neural text generators
may be more sensitive to various modeling choices than previously thought.

本文提出了一项新任务，即区分生成文本的几个变种中的哪一个，并进行了一系列诊断测试，以观察建模选择（例如取样方法，top-k 概率，模型架构等）是否在生成的文本中留下可检测的痕迹。我们的主要发现是，这些痕迹存在，并且不同的建模选择可以通过观察生成的文本来推断出来，这表明神经文本生成器可能比以前想象的更敏感于各种建模选择。