11 citations · 36 across the 18 of their papers we have counts for
18 papers
Embedding Models for Stance-Aware Argument Retrieval
Angelo Sparacino, Francesca Toni, Adam Dejl
In computational argumentation, obtaining arguments that explicitly support or attack given claims is a critical precursor to downstream reasoning tasks. When these supporting and…
A Theory of Post-hoc Debate Judgement
Xiang Yin, Adam Dejl, Antonio Rago +2
Debates have recently emerged as a useful methodology for agentic AI to improve performance as well as to aid explainability and user engagement. For example, LLM-empowered agents…
When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness
Mahdi Dhaini, Adam Dejl, Juraj Vladika +3
Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context learning (ICL). However, it re…
Neurosymbolic Learning for Inference-Time Argumentation
Gabriel Freedman, Adam Dejl, Adam Gould +4
Claim verification is an important problem in high-stakes settings, including health and finance. When information underpinning claims is incomplete or conflicting, uncertain answe…
Argumentation for Explainable and Globally Contestable Decision Support with LLMs
Adam Dejl, Matthew Williams, Francesca Toni
Large language models (LLMs) exhibit strong general capabilities, but their deployment in high-stakes domains is hindered by their opacity and unpredictability. Recent work has tak…
ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models
Adam Dejl, Deniz Gorur, Francesca Toni
Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with the aim of making the result…
EvalSense: A Framework for Domain-Specific LLM (Meta-)Evaluation
Adam Dejl, Jonathan Pearson
Robust and comprehensive evaluation of large language models (LLMs) is essential for identifying effective LLM system configurations and mitigating risks associated with deploying…
Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation
Adam Dejl, James Barry, Alessandra Pascale +1
Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce outputs that are incomplete or se…
Evaluating Uncertainty Quantification Methods in Argumentative Large Language Models
Kevin Zhou, Adam Dejl, Gabriel Freedman +3
Research in uncertainty quantification (UQ) for large language models (LLMs) is increasingly important towards guaranteeing the reliability of this groundbreaking technology. We ex…
XAI-Units: Benchmarking Explainability Methods with Unit Tests
Jun Rui Lee, Sadegh Emami, Michael David Hollins +5
Feature attribution (FA) methods are widely used in explainable AI (XAI) to help users understand how the inputs of a machine learning model contribute to its outputs. However, dif…
Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference
Xuehao Zhai, Junqi Jiang, Adam Dejl +4
Urban land use inference is a critically important task that aids in city planning and policy-making. Recently, the increased use of sensor and location technologies has facilitate…
Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts
Lihu Chen, Adam Dejl, Francesca Toni
Large Language Models (LLMs) possess vast amounts of knowledge within their parameters, prompting research into methods for locating and editing this knowledge. Previous work has l…
Contestable AI needs Computational Argumentation
Francesco Leofante, Hamed Ayoobi, Adam Dejl +10
AI has become pervasive in recent years, but state-of-the-art approaches predominantly neglect the need for AI systems to be contestable. Instead, contestability is advocated by AI…
Argumentative Large Language Models for Explainable and Contestable Claim Verification
Gabriel Freedman, Adam Dejl, Deniz Gorur +3
The profusion of knowledge encoded in large language models (LLMs) and their ability to apply this knowledge zero-shot in a range of settings makes them promising candidates for us…
A Knowledge Distillation Approach for Sepsis Outcome Prediction from Multivariate Clinical Time Series
Anna Wong, Shu Ge, Nassim Oufattole +4
Sepsis is a life-threatening condition triggered by an extreme infection response. Our objective is to forecast sepsis patient outcomes using their medical history and treatments,…
Hidden Conflicts in Neural Networks and Their Implications for Explainability
Adam Dejl, Dekai Zhang, Hamed Ayoobi +2
Artificial Neural Networks (ANNs) often represent conflicts between features, arising naturally during training as the network learns to integrate diverse and potentially disagreei…
RadGraph2: Modeling Disease Progression in Radiology Reports via Hierarchical Information Extraction
Sameer Khanna, Adam Dejl, Kibo Yoon +4
We present RadGraph2, a novel dataset for extracting information from radiology reports that focuses on capturing changes in disease state and device placement over time. We introd…
Treatment-RSPN: Recurrent Sum-Product Networks for Sequential Treatment Regimes
Adam Dejl, Harsh Deep, Jonathan Fei +2
Sum-product networks (SPNs) have recently emerged as a novel deep learning architecture enabling highly efficient probabilistic inference. Since their introduction, SPNs have been…