Search Results for author:
Found 43 papers, 7 papers with code
Representation Problems in Linguistic Annotations: Ambiguity, Variation, Uncertainty, Error and Bias
The development of linguistic corpora is fraught with various problems of annotation and representation.
Reward Learning from Multiple Feedback Types
Such diverse feedback can better support the goals of a human annotator, and the simultaneous use of multiple sources might be mutually informative for the learning process or carry type-dependent biases for the reward learning process.
Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework
Based on the feedback taxonomy and quality criteria, we derive requirements and design choices for systems learning from human feedback.
Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities
Our work investigates how the integration of information from image and text modalities influences the performance and behavior of VLMs in visual question answering (VQA) and reasoning tasks.
Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
Further, we comprehensively evaluate various XAI methods to assist practitioners in selecting appropriate methods aligning with their needs.
iNNspector: Visual, Interactive Deep Model Debugging
To operationalize our framework in a ready-to-use application, we (2) present the iNNspector system.
MelodyVis: Visual Analytics for Melodic Patterns in Sheet Music
Our study also confirms the usefulness of MelodyVis in supporting common analytical tasks in melodic analysis, with participants reporting improved pattern identification and interpretation.
On Affine Homotopy between Language Encoders
In this spirit, we study the properties of \emph{affine} alignment of language encoders and its implications on extrinsic similarity.
Challenges and Opportunities in Text Generation Explainability
The NLP community has begun to take a keen interest in gaining a deeper understanding of text generation, leading to the development of model-agnostic explainable artificial intelligence (xAI) methods tailored to this task.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Interactive Analysis of LLMs using Meaningful Counterfactuals
First, the generated textual counterfactuals should be meaningful and readable to users and thus can be mentally compared to draw conclusions.
Deconstructing Human-AI Collaboration: Agency, Interaction, and Adaptation
As full AI-based automation remains out of reach in most real-world applications, the focus has instead shifted to leveraging the strengths of both human and AI agents, creating effective collaborative systems.
generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation
Large language models (LLMs) are widely deployed in various downstream tasks, e. g., auto-completion, aided writing, or chat-based text generation.
SyntaxShap: Syntax-aware Explainability Method for Text Generation
We adopt a model-based evaluation to compare SyntaxShap and its weighted form to state-of-the-art explainability methods adapted to text generation tasks, using diverse metrics including faithfulness, coherency, and semantic alignment of the explanations to the model.
PowerGraph: A power grid benchmark dataset for graph neural networks
However, there is a lack of publicly available graph datasets for training and benchmarking ML models in electrical power grid applications.
RELIC: Investigating Large Language Model Responses using Self-Consistency
To address this challenge, we propose an interactive system that helps users gain insight into the reliability of the generated text.
A Diachronic Perspective on User Trust in AI under Uncertainty
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.
Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges
We quantitatively show the value of exposing the beam search tree and present five detailed analysis scenarios addressing the identified challenges.
GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations
Diverse explainability methods of graph neural networks (GNN) have recently been developed to highlight the edges and nodes in the graph that contribute the most to the model predictions.
RLHF-Blender: A Configurable Interactive Interface for Learning from Diverse Human Feedback
To use reinforcement learning from human feedback (RLHF) in practical applications, it is crucial to learn reward models from diverse sources of human feedback and to consider human factors involved in providing feedback of different types.
Visual Explanations with Attributions and Counterfactuals on Time Series Classification
To further inspect the model decision-making as well as potential data errors, a what-if analysis facilitates hypothesis generation and verification on both the global and local levels.
Which Spurious Correlations Impact Reasoning in NLI Models? A Visual Interactive Diagnosis through Data-Constrained Counterfactuals
We present a human-in-the-loop dashboard tailored to diagnosing potential spurious features that NLI models rely on for predictions.
Improving Explainability of Disentangled Representations using Multipath-Attribution Mappings
We propose a framework that utilizes interpretable disentangled representations for downstream-task prediction.
Automatic Generation of Socratic Subquestions for Teaching Math Word Problems
On both automatic and human quality evaluations, we find that LMs constrained with desirable question properties generate superior questions and improve the overall performance of a math word problem solver.
How to Enable Uncertainty Estimation in Proximal Policy Optimization
To overcome this, we formulate a Pareto optimization problem in which we simultaneously optimize for reward and OOD detection performance.
Deep Reinforcement Learning
Out of Distribution (OOD) Detection
+1
Characterizing Uncertainty in the Visual Text Analysis Pipeline
Current visual text analysis approaches rely on sophisticated processing pipelines.
BARReL: Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning
Robustness to adversarial perturbations has been explored in many areas of computer vision.
Visual Comparison of Language Model Adaptation
The simplicity of adapter training and composition comes along with new challenges, such as maintaining an overview of adapter properties and effectively comparing their produced embedding spaces.
Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language
Language models learn and represent language differently than humans; they learn the form and not the meaning.
From Correlation to Causation: Formalizing Interpretable Machine Learning as a Statistical Process
Based on these similarities, we present a formalization of IML along the lines of a statistical process.
BIG-bench Machine Learning
Explainable Artificial Intelligence (XAI)
+1
Humans are not Boltzmann Distributions: Challenges and Opportunities for Modelling Human Feedback and Interaction in Reinforcement Learning
Reinforcement learning (RL) commonly assumes access to well-specified reward functions, which many practical applications do not provide.
CorpusVis: Visual Analysis of Digital Sheet Music Collections
Manually investigating sheet music collections is challenging for music analysts due to the magnitude and complexity of underlying features, structures, and contextual information.
Explaining Contextualization in Language Models using Visual Analytics
Despite the success of contextualized language models on various NLP tasks, it is still unclear what these models really learn.
Curating Publications as Artefacts — Exploring Machine Learning Research in an Interactive Virtual Museum
The need for innovating scientific publications is felt across various research fields.
An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks
Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques.
BIG-bench Machine Learning
Explainable Artificial Intelligence (XAI)
+2
XplaiNLI: Explainable Natural Language Inference through Visual Analytics
Advances in Natural Language Inference (NLI) have helped us understand what state-of-the-art models really learn and what their generalization power is.
A Comparative Analysis of Industry Human-AI Interaction Guidelines
We have then used this framework to compare each of the surveyed companies to find differences in areas of emphasis.
Human-Computer Interaction
Should We Trust (X)AI? Design Dimensions for Structured Experimental Evaluations
This paper systematically derives design dimensions for the structured evaluation of explainable artificial intelligence (XAI) approaches.
Towards a Rigorous Evaluation of XAI Methods on Time Series
In this work, we apply XAI methods previously used in the image and text-domain on time series.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+2
Semantic Concept Spaces: Guided Topic Model Refinement using Word-Embedding Projections
We present a framework that allows users to incorporate the semantics of their domain knowledge for topic model refinement while remaining model-agnostic.
VIANA: Visual Interactive Annotation of Argumentation
The results show that experts prefer our system over existing solutions due to the speedup provided by the automatic suggestions and the tight integration between text and graph views.
explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models.
BIG-bench Machine Learning
Explainable Artificial Intelligence (XAI)
lingvis.io - A Linguistic Visual Analytics Framework
We present a modular framework for the rapid-prototyping of linguistic, web-based, visual analytics applications.
