Related papers: Re-defining Humor Data Objects for AI Humor Resear…

Reward modelling from preference data is a crucial step in aligning large language models (LLMs) with human values, requiring robust generalisation to novel prompt-response pairs. In this work, we propose to frame this problem in a causal…

Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…

The evolution of mathematics is shaped importantly by interestingness: researchers choose which problems to pursue, and students choose which problems to engage with, based on expectations of interest and challenge. As AI systems,…

This paper investigates the potential of AI models, particularly large language models (LLMs), to support knowledge exploration and augment human creativity during ideation. We present "Latent Lab" an interactive tool for discovering…

People acquire concepts through rich physical and social experiences and use them to understand and navigate the world. In contrast, large language models (LLMs), trained solely through next-token prediction on text, exhibit strikingly…

Artificial Intelligence (AI) has significantly advanced in recent years, driving innovation across various fields, especially in robotics. Even though robots can perform complex tasks with increasing autonomy, challenges remain in ensuring…

Large Language Models (LLMs) are revolutionizing the field of computing education with their powerful code-generating capabilities. Traditional pedagogical practices have focused on code writing tasks, but there is now a shift in importance…

Recent work has highlighted the importance of monitoring chain-of-thought reasoning for AI safety; however, current approaches that analyze textual reasoning steps can miss subtle harmful patterns and may be circumvented by models that hide…

Language's complexity is evident in the rich tapestry of slang expressions, often laden with humor and cultural nuances. This linguistic phenomenon has become increasingly prevalent, especially in digital communication. However, existing AI…

This study introduces a novel method for irony detection, applying Large Language Models (LLMs) with prompt-based learning to facilitate emotion-centric text augmentation. Traditional irony detection techniques typically fall short due to…

Attribution theory explains how individuals interpret and attribute others' behavior in a social context by employing personal (dispositional) and impersonal (situational) causality. Large Language Models (LLMs), trained on human-generated…

We propose misogyny detection as an Argumentative Reasoning task and we investigate the capacity of large language models (LLMs) to understand the implicit reasoning used to convey misogyny in both Italian and English. The central aim is to…

Large Language Models (LLMs) have been widely used as general-purpose AI agents showing comparable performance on many downstream tasks. However, existing work shows that it is challenging for LLMs to integrate structured data (e.g. KG,…

Temporal reasoning is a crucial NLP task, providing a nuanced understanding of time-sensitive contexts within textual data. Although recent advancements in LLMs have demonstrated their potential in temporal reasoning, the predominant focus…

We analyzed 83 persona prompts from 27 research articles that used large language models (LLMs) to generate user personas. Findings show that the prompts predominantly generate single personas. Several prompts express a desire for short or…

In this paper, we advance the study of AI-augmented reasoning in the context of Human-Computer Interaction (HCI), psychology and cognitive science, focusing on the critical task of visual perception. Specifically, we investigate the…

As general-purpose tools, Large Language Models (LLMs) must often reason about everyday physical environments. In a question-and-answer capacity, understanding the interactions of physical objects may be necessary to give appropriate…

The recent advent of reasoning models like OpenAI's o1 was met with excited speculation by the AI community about the mechanisms underlying these capabilities in closed models, followed by a rush of replication efforts, particularly from…

Although natural language is the default medium for Large Language Models (LLMs), its limited expressive capacity creates a profound bottleneck for complex problem-solving. While recent advancements in AI have relied heavily on scaling,…

With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively…