Related papers: Identifying Implicit Vulnerabilities through Perso…
This paper describes the process of developing data visualisations to enhance a commercial software platform for combating insider threat, whose existing UI, while perfectly functional, was limited in its ability to allow analysts to easily…
Our ability to predict the behavior of complex agents turns on the attribution of goals. Probing for goal-directed behavior comes in two flavors: Behavioral and mechanistic. The former proposes that goal-directedness can be estimated…
Automated methods for red teaming LLMs are an important tool to identify LLM vulnerabilities that may not be covered in static benchmarks, allowing for more thorough probing. They can also adapt to each specific LLM to discover weaknesses…
Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…
In multi-agent systems, the agents may have goals that depend on a social, shared interpretation about the facts occurring in the system. These are the so-called social goals. Artificial institutions provide such a social interpretation by…
This paper investigates the user experience of visualizations of a machine learning (ML) system that recognizes objects in images. This is important since even good systems can fail in unexpected ways as misclassifications on photo-sharing…
Personas are a valuable tool for discussing accessibility requirements in software design and development practices. However, the use of personas for accessibility-focused requirements elicitation in VR projects remains limited and is…
Many interactive data systems combine visual representations of data with embedded algorithmic support for automation and data exploration. To effectively support transparent and explainable data systems, it is important for researchers and…
Goal recognition (GR) involves inferring an agent's unobserved goal from a sequence of observations. This is a critical problem in AI with diverse applications. Traditionally, GR has been addressed using 'inference to the best explanation'…
Mobile applications increasingly rely on sensor data to infer user context and deliver personalized experiences. Yet the mechanisms behind this personalization remain opaque to users and researchers alike. This paper presents a sandbox…
The mental models that humans form of other agents---encapsulating human beliefs about agent goals, intentions, capabilities, and more---create an underlying basis for interaction. These mental models have the potential to affect both the…
Current works in the generation of personalized dialogue primarily contribute to the agent presenting a consistent personality and driving a more informative response. However, we found that the generated responses from most previous models…
In human-agent teams, openly sharing goals is often assumed to enhance planning, collaboration, and effectiveness. However, direct communication of these goals is not always feasible, requiring teammates to infer their partner's intentions…
As language models achieve increasingly human-like capabilities in conversational text generation, a critical question emerges: to what extent can these systems simulate the characteristics of specific individuals? To evaluate this, we…
Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…
As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gender and racial biases) has come to the fore of the public's…
When inferring the goals that others are trying to achieve, people intuitively understand that others might make mistakes along the way. This is crucial for activities such as teaching, offering assistance, and deciding between blame or…
Goal recognition aims at predicting human intentions from a trace of observations. This ability allows people or organizations to anticipate future actions and intervene in a positive (collaborative) or negative (adversarial) way. Goal…
Scaling and sustaining educational innovations is a common problem in the learning sciences. Professional development resources around educational innovations that are personalized to appeal to the needs and motivations of different types…
We introduce a framework that predicts the goals behind observable human action in video. Motivated by evidence in developmental psychology, we leverage video of unintentional action to learn video representations of goals without direct…