124 citations · 344 across the 42 of their papers we have counts for
47 papers
Human agency in initial human-AI proof formalization workflows
Katherine M. Collins, Simon Frieder, Jonas Bayer +14
For centuries, human mathematicians have written proofs to substantiate their mathematical arguments; yet, the ability to automatically verify the validity of proofs has long been…
Learning to Orchestrate Agents under Uncertainty
Mary Chriselda Antony Oliver, Lan Jiang, Aaron Bundi Anampiu +3
Adaptive orchestration of heterogeneous agents requires making sequential delegation decisions under uncertain and evolving agent behaviour, e.g., coordinating specialised AI model…
RCTs for Frontier AI Governance: Methodological Challenges and Solutions for Human Uplift Studies
Patricia Paskov, Kevin Wei, Shen Zhou Hong +7
Human uplift studies, or studies that measure the effects of AI access on human performance via randomized controlled trials (RCT) or similar methodologies, increasingly inform fro…
Beyond Quantification: Navigating Uncertainty in Professional AI Systems
Sylvie Delacroix, Diana Robinson, Umang Bhatt +12
The growing integration of large language models across professional domains transforms how experts make critical decisions in healthcare, education, and law. While significant res…
Measuring and mitigating overreliance to build human-compatible AI
Lujain Ibrahim, Katherine M. Collins, Sunnie S. Y. Kim +14
Large language models (LLMs) distinguish themselves from previous technologies by functioning as collaborative ``thought partners,'' capable of engaging more fluidly in natural lan…
Documenting Deployment with Fabric: A Repository of Real-World AI Governance
Mackenzie Jorgensen, Kendall Brogle, Katherine M. Collins +10
Artificial intelligence (AI) is increasingly integrated into society, from financial services and traffic management to creative writing. Academic literature on the deployment of A…
Unequal Uncertainty: Rethinking Algorithmic Interventions for Mitigating Discrimination from AI
Holli Sargeant, Mackenzie Jorgensen, Arina Shah +3
Uncertainty in artificial intelligence (AI) predictions raises pressing legal and ethical questions for AI-assisted decision-making. This article examines two uncertainty-based alg…
When Should We Orchestrate Multiple Agents?
Umang Bhatt, Sanyam Kapoor, Mihir Upadhyay +6
Strategies for orchestrating the interactions between multiple agents, both human and artificial, can wildly overestimate performance and underestimate the cost of orchestration. W…
Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems
Matthew Barker, Andrew Bell, Evan Thomas +3
While Retrieval Augmented Generation (RAG) has emerged as a popular technique for improving Large Language Model (LLM) systems, it introduces a large number of choices, parameters…
Revisiting Rogers' Paradox in the Context of Human-AI Interaction
Katherine M. Collins, Umang Bhatt, Ilia Sucholutsky
Humans learn about the world, and how to act in the world, in many ways: from individually conducting experiments to observing and reproducing others' behavior. Different learning…
Building Machines that Learn and Think with People
Katherine M. Collins, Ilia Sucholutsky, Umang Bhatt +10
What do we want from machine intelligence? We envision machines that are not just tools for thought, but partners in thought: reasonable, insightful, knowledgeable, reliable, and t…
Modulating Language Model Experiences through Frictions
Katherine M. Collins, Valerie Chen, Ilia Sucholutsky +6
Language models are transforming the ways that their users engage with the world. Despite impressive capabilities, over-consumption of language model outputs risks propagating unch…
Large Language Models Must Be Taught to Know What They Don't Know
Sanyam Kapoor, Nate Gruver, Manley Roberts +7
When using large language models (LLMs) in high-stakes applications, we need to know when we can trust their predictions. Some works argue that prompting high-performance LLMs is s…
Representational Alignment Supports Effective Machine Teaching
Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya +11
A good teacher should not only be knowledgeable, but should also be able to communicate in a way that the student understands -- to share the student's representation of the world.…
Towards interactive evaluations for interaction harms in human-AI systems
Lujain Ibrahim, Saffron Huang, Umang Bhatt +2
Current AI evaluation methods, which rely on static, model-only tests, fail to account for harms that emerge through sustained human-AI interaction. As AI systems proliferate and a…
FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Matthew Barker, Emma Kallina, Dhananjay Ashok +6
Even though machine learning (ML) pipelines affect an increasing array of stakeholders, there is little work on how input from stakeholders is recorded and incorporated. We propose…
Selective Concept Models: Permitting Stakeholder Customisation at Test-Time
Matthew Barker, Katherine M. Collins, Krishnamurthy Dvijotham +2
Concept-based models perform prediction using a set of concepts that are interpretable to stakeholders. However, such models often involve a fixed, large number of concepts, which…
Evaluating Language Models for Mathematics through Interactions
Katherine M. Collins, Albert Q. Jiang, Simon Frieder +11
There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants. However, the standard methodology of e…
Learning Personalized Decision Support Policies
Umang Bhatt, Valerie Chen, Katherine M. Collins +4
Individual human decision-makers may benefit from different forms of support to improve decision outcomes, but when each form of support will yield better outcomes? In this work, w…
Human Uncertainty in Concept-Based AI Systems
Katherine M. Collins, Matthew Barker, Mateo Espinosa Zarlenga +6
Placing a human in the loop may abate the risks of deploying AI systems in safety-critical settings (e.g., a clinician working with a medical AI system). However, mitigating risks…
Harms from Increasingly Agentic Algorithmic Systems
Alan Chan, Rebecca Salganik, Alva Markelius +19
Research in Fairness, Accountability, Transparency, and Ethics (FATE) has established many sources and forms of algorithmic harm, in domains as diverse as health care, finance, pol…
Towards Robust Metrics for Concept Representation Evaluation
Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams +4
Recent work on interpretability has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as conc…
Human-in-the-Loop Mixup
Katherine M. Collins, Umang Bhatt, Weiyang Liu +4
Aligning model representations to humans has been found to improve robustness and generalization. However, such methods often focus on standard observational data. Synthetic data i…
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis
Yuxin Xiao, Paul Pu Liang, Umang Bhatt +3
Pre-trained language models (PLMs) have gained increasing popularity due to their compelling prediction performance in diverse natural language processing (NLP) tasks. When formula…