Suspense is an affective response to narrative text that is believed to involve complex cognitive processes in humans. Several psychological models have been developed to describe this phenomenon and the circumstances under which text might trigger it. We replicate four seminal psychological studies of human perceptions of suspense, substituting human responses with those of different open-weight and closed-source LMs. We conclude that while LMs can distinguish whether a text is intended to induce suspense in people, LMs cannot accurately estimate the relative amount of suspense within a text sequence as compared to human judgments, nor can LMs properly capture the human perception for the rise and fall of suspense across multiple text segments. We probe the abilities of LM suspense understanding by adversarially permuting the story text to identify what cause human and LM perceptions of suspense to diverge. We conclude that, while LMs can superficially identify and track certain facets of suspense, they do not process suspense in the same way as human readers.

Generative Artificial Intelligence (AI) encounters limitations in efficiency and fairness within the realm of Procedural Content Generation (PCG) when human creators solely drive and bear responsibility for the generative process. Alternative setups, such as Mixed-Initiative Co-Creative (MI-CC) systems, exhibited their promise. Still, the potential of an active mixed initiative, where AI takes a role beyond following, is understudied. This work investigates the influence of the adaptive ability of an active and learning AI agent on creators' expectancy of creative responsibilities in an MI-CC setting. We built and studied a system that employs reinforcement learning (RL) methods to learn the creative responsibility preferences of a human user during online interactions. Situated in story co-creation, we develop a Multi-armed-bandit agent that learns from the human creator, updates its collaborative decision-making belief, and switches between its capabilities during an MI-CC experience. With 39 participants joining a human subject study, Our developed system's learning capabilities are well recognized compared to the non-learning ablation, corresponding to a significant increase in overall satisfaction with the MI-CC experience. These findings indicate a robust association between effective MI-CC collaborative interactions, particularly the implementation of proactive AI initiatives, and deepened understanding among all participants.

Imaginative play is an area of creativity that could allow robots to engage with the world around them in a much more personified way. Imaginary play can be seen as taking real objects and locations and using them as imaginary objects and locations in virtual scenarios. We adopted the story generation capability of large language models (LLMs) to obtain the stories used for imaginary play with human-written prompts. Those generated stories will be simplified and mapped into action sequences that can guide the agent in imaginary play. To evaluate whether the agent can successfully finish the imaginary play, we also designed a text adventure game to simulate a house as the playground for the agent to interact.

Language models pre-trained on large self-supervised corpora, followed by task-specific fine-tuning has become the dominant paradigm in NLP. These pre-training datasets often have a one-to-many structure--e.g. in dialogue there are many valid responses for a given context. However, only some of these responses will be desirable in our downstream task. This raises the question of how we should train the model such that it can emulate the desirable behaviours, but not the undesirable ones. Current approaches train in a one-to-one setup--only a single target response is given for a single dialogue context--leading to models only learning to predict the average response, while ignoring the full range of possible responses. Using text-based games as a testbed, our approach, PASA, uses discrete latent variables to capture the range of different behaviours represented in our larger pre-training dataset. We then use knowledge distillation to distil the posterior probability distribution into a student model. This probability distribution is far richer than learning from only the hard targets of the dataset, and thus allows the student model to benefit from the richer range of actions the teacher model has learned. Results show up to 49% empirical improvement over the previous state-of-the-art model on the Jericho Walkthroughs dataset.

Controlled automated story generation seeks to generate natural language stories satisfying constraints from natural language critiques or preferences. Existing methods to control for story preference utilize prompt engineering which is labor intensive and often inconsistent. They may also use logit-manipulation methods which require annotated datasets to exist for the desired attributes. To address these issues, we first train a contrastive bi-encoder model to align stories with corresponding human critiques, named CARP, building a general purpose preference model. This is subsequently used as a reward function to fine-tune a generative language model via reinforcement learning. However, simply fine-tuning a generative language model with a contrastive reward Figure 1: Illustration of our technique for generating model does not always reliably result in story content controlled by preferences. A language a story generation system capable of generating model generates candidates, which are ranked stories that meet user preferences. To increase by the CARP model to produce scores. The scores are story generation robustness we further used to fine-tune the language model to produce higher fine-tune the contrastive reward model using a scoring--and thus more aligned with preferences-- prompt-learning technique.

There is a growing frustration amongst researchers and developers in Explainable AI (XAI) around the lack of consensus around what is meant by 'explainability'. Do we need one definition of explainability to rule them all? In this paper, we argue why a singular definition of XAI is neither feasible nor desirable at this stage of XAI's development. We view XAI through the lenses of Social Construction of Technology (SCOT) to explicate how diverse stakeholders (relevant social groups) have different interpretations (interpretative flexibility) that shape the meaning of XAI. Forcing a standardization (closure) on the pluralistic interpretations too early can stifle innovation and lead to premature conclusions. We share how we can leverage the pluralism to make progress in XAI without having to wait for a definitional consensus.

It's a situation familiar to anyone who's ever communicated with a voice assistant on a smart device. You pose a request: "Hey Voice Assistant, tell me a story about Georgia Tech." More often than not, you get a related response – "Georgia Tech is located in Atlanta, Georgia. Would you like me to provide you with directions?" – but one with slightly unnatural language and only limited information. Despite the enormous strides made in artificial intelligence to develop systems that can answer simple questions and requests, the kinds of natural conversational language humans have with each other when giving more complex directions or telling stories has thus far been out of reach.

The advent of large pre-trained generative language models has provided a common framework for AI story generation via sampling the model to create sequences that continue the story. However, sampling alone is insufficient for story generation. In particular, it is hard to direct a language model to create stories to reach a specific goal event. We present two automated techniques grounded in deep reinforcement learning and reward shaping to control the plot of computer-generated stories. The first utilizes proximal policy optimization to fine-tune an existing transformer-based language model to generate text continuations but also be goal-seeking. The second extracts a knowledge graph from the unfolding story, which is used by a policy network with graph attention to select a candidate continuation generated by a language model. We report on automated metrics pertaining to how often stories achieve a given goal event as well as human participant rankings of coherence and overall story quality compared to baselines and ablations.

Artificial intelligence researchers don't like it when you ask them to name the top AI labs in the world, possibly because it's so hard to answer. There are some obvious contenders when it comes to commercial AI labs. U.S. Big Tech -- Google, Facebook, Amazon, Apple and Microsoft -- have all set up dedicated AI labs over the last decade. There's also DeepMind, which is owned by Google parent company Alphabet, and OpenAI, which counts Elon Musk as a founding investor. "Wow, I hate this question," Mark Riedl, associate professor at the Georgia Tech School of Interactive Computing, told CNBC when asked to pick his standouts.

For all GPT-3's flair, its output can feel untethered from reality, as if it doesn't know what it's talking about. By grounding text in images, researchers at OpenAI and elsewhere are trying to give language models a better grasp of the everyday concepts that humans use to make sense of things. DALL·E and CLIP come at this problem from different directions. At first glance, CLIP (Contrastive Language-Image Pre-training) is yet another image recognition system. Except that it has learned to recognize images not from labeled examples in curated data sets, as most existing models do, but from images and their captions taken from the internet.