Related papers: WHAT-IF: Exploring Branching Narratives by Meta-Pr…
Agents powered by large language models have shown remarkable abilities in solving complex tasks. However, most agent systems remain reactive, limiting their effectiveness in scenarios requiring foresight and autonomous decision-making. In…
The zero-shot chain of thought (CoT) approach is often used in question answering (QA) by language models (LMs) for tasks that require multiple reasoning steps. However, some QA tasks hinge more on accessing relevant knowledge than on…
Strategic decision-making involves interactive reasoning where agents adapt their choices in response to others, yet existing evaluations of large language models (LLMs) often emphasize Nash Equilibrium (NE) approximation, overlooking the…
Interactive fiction games have emerged as an important application to improve the generalization capabilities of language-based reinforcement learning (RL) agents. Existing environments for interactive fiction games are domain-specific or…
Counterfactual explanations (CFs) offer human-centric insights into machine learning predictions by highlighting minimal changes required to alter an outcome. Therefore, CFs can be used as (i) interventions for abnormality prevention and…
Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods often perform suboptimally, mainly due to a lack of detailed,…
Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual…
Large language models (LLMs) exhibit impressive proficiency in natural language generation, understanding user instructions, and emulating human-like language use, which has led to significant interest in their application to role-playing…
With the advancement of natural language generation (NLG) technologies, creative story generation systems have gained increasing attention. However, current systems often fail to accurately translate user intent into satisfactory story…
Large language models (LLMs) have demonstrated impressive performance in mathematical and commonsense reasoning tasks using chain-of-thought (CoT) prompting techniques. But can they perform emotional reasoning by concatenating `Let's think…
Large language models have demonstrated their capabilities in storyline creation and human-like character role-playing. Current language model agents mainly focus on reasonable behaviors from the level of individuals, and their behaviors…
While generative AI is advancing writing support tools, creative writing is often seen as the exclusive domain of skilled writers. This paper introduces "1001 Nights", a co-creative story-crafting game that transforms writing into a playful…
Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conventional wisdom about in-context few-shot learning. To investigate this few-shot dilemma, we…
Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental issue -- the predetermined…
Reading stories evokes rich interpretive, affective, and evaluative responses, such as inferences about narrative intent or judgments about characters. Yet, computational models of reader response are limited, preventing nuanced analyses.…
Interactive digital stories provide a sense of flexibility and freedom to players by allowing them to make choices at key junctions. These choices advance the narrative and determine, to some degree, how the story evolves for that player.…
Large Language Models (LLMs) are increasingly being deployed as the reasoning engines for agentic AI systems, yet they exhibit a critical flaw: a rigid adherence to explicit rules that leads to decisions misaligned with human common sense…
This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, villain, and victim…
Stories are central to human culture, serving to share ideas, preserve traditions, and foster connections. Automatic story generation, a key advancement in artificial intelligence (AI), offers new possibilities for creating personalized…
We propose an interactive multimodal framework for language learning. Instead of being passively exposed to large amounts of natural text, our learners (implemented as feed-forward neural networks) engage in cooperative referential games…