Negation is a fundamental aspect of natural language, playing a critical role in communication and comprehension. Our study assesses the negation detection performance of Generative Pre-trained Transformer (GPT) models, specifically GPT-2, GPT-3, GPT-3.5, and GPT-4. We focus on the identification of negation in natural language using a zero-shot prediction approach applied to our custom xNot360 dataset. Our approach examines sentence pairs labeled to indicate whether the second sentence negates the first. Our findings expose a considerable performance disparity among the GPT models, with GPT-4 surpassing its counterparts and GPT-3.5 displaying a marked performance reduction. The overall proficiency of the GPT models in negation detection remains relatively modest, indicating that this task pushes the boundaries of their natural language understanding capabilities. We not only highlight the constraints of GPT models in handling negation but also emphasize the importance of logical reliability in high-stakes domains such as healthcare, science, and law.
We introduce DR-HAI -- a novel argumentation-based framework designed to extend model reconciliation approaches, commonly used in explainable AI planning, for enhanced human-AI interaction. By adopting a multi-shot reconciliation paradigm and not assuming a-priori knowledge of the human user's model, DR-HAI enables interactive reconciliation to address knowledge discrepancies between an explainer and an explainee. We formally describe the operational semantics of DR-HAI, provide theoretical guarantees related to termination and success, and empirically evaluate its efficacy. Our findings suggest that DR-HAI offers a promising direction for fostering effective human-AI interactions.
We propose a novel approach to logic-based learning which generates assumption-based argumentation (ABA) frameworks from positive and negative examples, using a given background knowledge. These ABA frameworks can be mapped onto logic programs with negation as failure that may be non-stratified. Whereas existing argumentation-based methods learn exceptions to general rules by interpreting the exceptions as rebuttal attacks, our approach interprets them as undercutting attacks. Our learning technique is based on the use of transformation rules, including some adapted from logic program transformation rules (notably folding) as well as others, such as rote learning and assumption introduction. We present a general strategy that applies the transformation rules in a suitable order to learn stratified frameworks, and we also propose a variant that handles the non-stratified case. We illustrate the benefits of our approach with a number of examples, which show that, on one hand, we are able to easily reconstruct other logic-based learning approaches and, on the other hand, we can work out in a very simple and natural way problems that seem to be hard for existing techniques.
Assumption-based Argumentation (ABA) is a well-known structured argumentation formalism, whereby arguments and attacks between them are drawn from rules, defeasible assumptions and their contraries. A common restriction imposed on ABA frameworks (ABAFs) is that they are flat, i.e., each of the defeasible assumptions can only be assumed, but not derived. While it is known that flat ABAFs can be translated into abstract argumentation frameworks (AFs) as proposed by Dung, no translation exists from general, possibly non-flat ABAFs into any kind of abstract argumentation formalism. In this paper, we close this gap and show that bipolar AFs (BAFs) can instantiate general ABAFs. To this end we develop suitable, novel BAF semantics which borrow from the notion of deductive support. We investigate basic properties of our BAFs, including computational complexity, and prove the desired relation to ABAFs under several semantics. Finally, in order to support computation and explainability, we propose the notion of dispute trees for our BAF semantics.
As the field of explainable AI (XAI) is maturing, calls for interactive explanations for (the outputs of) AI models are growing, but the state-of-the-art predominantly focuses on static explanations. In this paper, we focus instead on interactive explanations framed as conflict resolution between agents (i.e. AI models and/or humans) by leveraging on computational argumentation. Specifically, we define Argumentative eXchanges (AXs) for dynamically sharing, in multi-agent systems, information harboured in individual agents' quantitative bipolar argumentation frameworks towards resolving conflicts amongst the agents. We then deploy AXs in the XAI setting in which a machine and a human interact about the machine's predictions. We identify and assess several theoretical properties characterising AXs that are suitable for XAI. Finally, we instantiate AXs for XAI by defining various agent behaviours, e.g. capturing counterfactual patterns of reasoning in machines and highlighting the effects of cognitive biases in humans. We show experimentally (in a simulated environment) the comparative advantages of these behaviours in terms of conflict resolution, and show that the strongest argument may not always be the most effective.
Neural networks (NNs) have various applications in AI, but explaining their decision process remains challenging. Existing approaches often focus on explaining how changing individual inputs affects NNs' outputs. However, an explanation that is consistent with the input-output behaviour of an NN is not necessarily faithful to the actual mechanics thereof. In this paper, we exploit relationships between multi-layer perceptrons (MLPs) and quantitative argumentation frameworks (QAFs) to create argumentative explanations for the mechanics of MLPs. Our SpArX method first sparsifies the MLP while maintaining as much of the original mechanics as possible. It then translates the sparse MLP into an equivalent QAF to shed light on the underlying decision process of the MLP, producing global and/or local explanations. We demonstrate experimentally that SpArX can give more faithful explanations than existing approaches, while simultaneously providing deeper insights into the actual reasoning process of MLPs.
Random forests are decision tree ensembles that can be used to solve a variety of machine learning problems. However, as the number of trees and their individual size can be large, their decision making process is often incomprehensible. In order to reason about the decision process, we propose representing it as an argumentation problem. We generalize sufficient and necessary argumentative explanations using a Markov network encoding, discuss the relevance of these explanations and establish relationships to families of abductive explanations from the literature. As the complexity of the explanation problems is high, we discuss a probabilistic approximation algorithm and present first experimental results.
The natural way of obtaining different perspectives on any given topic is by conducting a debate, where participants argue for and against the topic. Here, we propose a novel debate framework for understanding the classifier's reasoning for making a particular prediction by modelling it as a multiplayer sequential zero-sum game. The players aim to maximise their utilities by adjusting their arguments with respect to other players' counterarguments. The contrastive nature of our framework encourages players to put forward diverse arguments, picking up the reasoning trails missed by their opponents. Thus, our framework answers the question: why did the classifier make a certain prediction?, by allowing players to argue for and against the classifier's decision. In the proposed setup, given the question and the classifier's latent knowledge, both agents take turns in proposing arguments to support or contradict the classifier's decision; arguments here correspond to the selection of specific features from the discretised latent space of the continuous classifier. By the end of the debate, we collect sets of supportive and manipulative features, serving as an explanation depicting the internal reasoning of the classifier. We demonstrate our Visual Debates on the geometric SHAPE and MNIST datasets for subjective validation, followed by the high-resolution AFHQ dataset. For further investigation, our framework is available at \url{https://github.com/koriavinash1/VisualDebates}.
We define a novel neuro-symbolic framework, argumentative reward learning, which combines preference-based argumentation with existing approaches to reinforcement learning from human feedback. Our method improves prior work by generalising human preferences, reducing the burden on the user and increasing the robustness of the reward model. We demonstrate this with a number of experiments.
The use of counterfactual explanations (CFXs) is an increasingly popular explanation strategy for machine learning models. However, recent studies have shown that these explanations may not be robust to changes in the underlying model (e.g., following retraining), which raises questions about their reliability in real-world applications. Existing attempts towards solving this problem are heuristic, and the robustness to model changes of the resulting CFXs is evaluated with only a small number of retrained models, failing to provide exhaustive guarantees. To remedy this, we propose the first notion to formally and deterministically assess the robustness (to model changes) of CFXs for neural networks, that we call {\Delta}-robustness. We introduce an abstraction framework based on interval neural networks to verify the {\Delta}-robustness of CFXs against a possibly infinite set of changes to the model parameters, i.e., weights and biases. We then demonstrate the utility of this approach in two distinct ways. First, we analyse the {\Delta}-robustness of a number of CFX generation methods from the literature and show that they unanimously host significant deficiencies in this regard. Second, we demonstrate how embedding {\Delta}-robustness within existing methods can provide CFXs which are provably robust.