Related papers: Accounting for Sycophancy in Language Model Uncert…

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

As artificial intelligence (AI) systems, particularly large language models (LLMs), become increasingly integrated into decision-making processes, the ability to trust their outputs is crucial. To earn human trust, LLMs must be well…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

As machine learning models are increasingly employed to assist human decision-makers, it becomes critical to communicate the uncertainty associated with these model predictions. However, the majority of work on uncertainty has focused on…

Understanding uncertainty plays a critical role in achieving common ground (Clark et al.,1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging…

Recommender systems rely heavily on user feedback to learn effective user and item representations. Despite their widespread adoption, limited attention has been given to the uncertainty inherent in the feedback used to train these systems.…

As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically express confidence through epistemic markers (e.g., "fairly confident") instead of numerical…

The conformity effect describes the tendency of individuals to align their responses with the majority. Studying this bias in large language models (LLMs) is crucial, as LLMs are increasingly used in various information-seeking and…

The widespread adoption of machine learning surrogate models has significantly improved the scale and complexity of systems and processes that can be explored accurately and efficiently using atomistic modeling. However, the inherently…

The increasing integration of Large Language Models (LLMs) into decision-making frameworks has exposed significant vulnerabilities to social compliance, specifically sycophancy and conformity. However, a critical research gap exists…

Clarification questions are an essential dialogue tool to signal misunderstanding, ambiguities, and under-specification in language use. While humans are able to resolve uncertainty by asking questions since childhood, modern dialogue…

Machine learning algorithms are increasingly used to assist human decision-making. When the goal of machine assistance is to improve the accuracy of human decisions, it might seem appealing to design ML algorithms that complement human…

The emergence of Large Language Models (LLMs) has revealed a growing need for human-AI collaboration, especially in creative decision-making scenarios where trust and reliance are paramount. Through human studies and model evaluations on…

Large Language Models exhibit sycophancy: prioritizing agreeableness over correctness. Current remedies evaluate reasoning outcomes: RLHF rewards correct answers, self-correction critiques outputs. All require ground truth, which is often…

A myriad of explainability methods have been proposed in recent years, but there is little consensus on how to evaluate them. While automatic metrics allow for quick benchmarking, it isn't clear how such metrics reflect human interaction…

In a human-AI collaboration, users build a mental model of the AI system based on its reliability and how it presents its decision, e.g. its presentation of system confidence and an explanation of the output. Modern NLP systems are often…

Recent research revealed a considerable lack of reliability for user feedback when interacting with adaptive systems, often denoted as user noise or human uncertainty. Moreover, this lack of reliability holds striking impacts for the…

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, these models could offer biased, hallucinated, or non-factual responses camouflaged by their fluency and realistic appearance. Uncertainty…

Stochastic simulation is widely used to study complex systems composed of various interconnected subprocesses, such as input processes, routing and control logic, optimization routines, and data-driven decision modules. In practice, these…

For safe and reliable deployment in the real world, autonomous agents must elicit appropriate levels of trust from human users. One method to build trust is to have agents assess and communicate their own competencies for performing given…