Search Results for author:
Found 34 papers, 13 papers with code
Modulating Language Model Experiences through Frictions
Through a user study with real humans, we observe shifts in user behavior from the imposition of a friction over LLMs in the context of a multi-topic question-answering task as a representative task that people may use LLMs for, e. g., in education and information retrieval.
Large Language Models Must Be Taught to Know What They Don't Know
We show that a thousand graded examples are sufficient to outperform baseline methods and that training through the features of a model is necessary for good performance and tractable for large open-source models when using LoRA.
Representational Alignment Supports Effective Machine Teaching
A good teacher should not only be knowledgeable; but should be able to communicate in a way that the student understands -- to share the student's representation of the world.
When Should Algorithms Resign? A Proposal for AI Governance
Algorithmic resignation is a strategic approach for managing the use of artificial intelligence (AI) by embedding governance directly into AI systems.
Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
To investigate the effect language on the formation of abstractions, we implement a novel multimodal serial reproduction framework by asking people who receive a visual stimulus to reproduce it in a linguistic format, and vice versa.
FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
We propose FeedbackLogs, addenda to existing documentation of ML pipelines, to track the input of multiple stakeholders.
Selective Concept Models: Permitting Stakeholder Customisation at Test-Time
Concept-based models perform prediction using a set of concepts that are interpretable to stakeholders.
Evaluating Language Models for Mathematics through Interactions
There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants.
Learning Personalized Decision Support Policies
$\texttt{Modiste}$ leverages stochastic contextual bandit techniques to personalize a decision support policy for each decision-maker and supports extensions to the multi-objective setting to account for auxiliary objectives like the cost of support.
Human Uncertainty in Concept-Based AI Systems
We study how existing concept-based models deal with uncertain interventions from humans using two novel datasets: UMNIST, a visual dataset with controlled simulated uncertainty based on the MNIST dataset, and CUB-S, a relabeling of the popular CUB concept dataset with rich, densely-annotated soft labels from humans.
Towards Robust Metrics for Concept Representation Evaluation
In this paper, we show that such metrics are not appropriate for concept learning and propose novel metrics for evaluating the purity of concept representations in both approaches.
Human-in-the-Loop Mixup
We focus on the synthetic data used in mixup: a powerful regularizer shown to improve model robustness, generalization, and calibration.
On the Informativeness of Supervision Signals
Supervised learning typically focuses on learning transferable representations from training examples annotated by humans.
Iterative Teaching by Data Hallucination
We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i. e., a pool of finite samples), which greatly limits the teacher's capability.
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis
In particular, there are various considerations behind the pipeline: (1) the choice and (2) the size of PLM, (3) the choice of uncertainty quantifier, (4) the choice of fine-tuning loss, and many more.
Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users
In this paper, we report on ongoing work regarding (i) the development of an AI system for flagging and explaining low-quality medical images in real-time, (ii) an interview study to understand the explanation needs of stakeholders using the AI system at OurCompany, and, (iii) a longitudinal user study design to examine the effect of including explanations on the workflow of the technicians in our clinics.
Eliciting and Learning with Soft Labels from Every Annotator
Our elicitation methodology therefore shows nuanced promise in enabling practitioners to enjoy the benefits of improved model performance and reliability with fewer annotators, and serves as a guide for future dataset curators on the benefits of leveraging richer information, such as categorical uncertainty, from individual annotators.
Perspectives on Incorporating Expert Feedback into Model Updates
A practitioner may receive feedback from an expert at the observation- or domain-level, and convert this feedback into updates to the dataset, loss function, or parameter space.
On the Utility of Prediction Sets in Human-AI Teams
We explore how such prediction sets impact expert decision-making in human-AI teams.
Approximating Full Conformal Prediction at Scale via Influence Functions
We prove that our method is a consistent approximation of full CP, and empirically show that the approximation error becomes smaller as the training set increases; e. g., for $10^{3}$ training points the two methods output p-values that are $<10^{-3}$ apart: a negligible error for any practical application.
Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating a single Counterfactual Latent Uncertainty Explanation (CLUE) for a given data point where the model is uncertain, identifying a single, on-manifold change to the input such that the model becomes more certain in its prediction.
On The Quality Assurance Of Concept-Based Representations
Recent work on Explainable AI has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as concepts.
DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
In this work, we take a step towards finding influential training points that also represent the training data well.
Do Concept Bottleneck Models Learn as Intended?
Concept bottleneck models map from raw inputs to concepts, and then from concepts to targets.
δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates
To interpret uncertainty estimates from differentiable probabilistic models, recent work has proposed generating Counterfactual Latent Uncertainty Explanations (CLUEs).
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders.
On the Fairness of Causal Algorithmic Recourse
Algorithmic fairness is typically studied from the perspective of predictions.
Machine Learning Explainability for External Stakeholders
As machine learning is increasingly deployed in high-stakes contexts affecting people's livelihoods, there have been growing calls to open the black box and to make machine learning algorithms more explainable.
Getting a CLUE: A Method for Explaining Uncertainty Estimates
Both uncertainty estimation and interpretability are important factors for trustworthy machine learning systems.
Evaluating and Aggregating Feature-based Model Explanations
A feature-based model explanation denotes how much each input feature contributes to a model's output for a given data point.
Explainable Machine Learning in Deployment
Yet there is little understanding of how organizations use these methods in practice.
Towards Aggregating Weighted Feature Attributions
Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution.
On Network Science and Mutual Information for Explaining Deep Neural Networks
In this paper, we present a new approach to interpret deep learning models.
The Impact of Humanoid Affect Expression on Human Behavior in a Game-Theoretic Setting
In this pilot study, we investigate (1) in what way a robot can express a certain mood to influence a human's decision making behavioral model; (2) how and to what extent the human will be influenced in a game theoretic setting.
