Search

Probabilistic Argumentation supports a form of hybrid reasoning by integrating quantitative (probabilistic) reasoning and qualitative argumentation in a natural way. Jury-based Probabilistic Argumentation supports the combination of opinions by different reasoners. In this paper we show how Jury-based Probabilistic Abstract Argumentation (JPAA) and a form of Jury-based Probabilistic Assumptionbased Argumentation (JPABA) can naturally support forecasting, whereby subjective probability estimates are combined to make predictions about future occurrences of events. The form of JPABA we consider is an instance of JPAA and results from integrating Assumption-Based Argumentation (ABA) and probability spaces expressed by Bayesian networks, under the so-called constellation approach. It keeps the underlying structured argumentation and probabilistic reasoning modules separate while integrating them. We show how JPAA and (the considered form of) JPABA can be used to support forecasting by 1) supporting different forecasters (jurors) to determine the probability of arguments (and, in the JPABA case, sentences) with respect to their own probability spaces, while sharing arguments (and their components); and 2) supporting the aggregation of individual forecasts to produce group forecasts.

Logic programming has long being advocated for legal reasoning, and several approaches have been put forward relying upon explicit representation of the law in logic programming terms. In this position paper we focus on the PROLEG logic-programming-based framework for formalizing and reasoning with Japanese presupposed ultimate fact theory. Specifically, we examine challenges and opportunities in leveraging deep learning techniques for improving legal reasoning using PROLEG, identifying four distinct options ranging from enhancing fact extraction using deep learning to end-to-end solutions for reasoning with textual legal descriptions. We assess advantages and limitations of each option, considering their technical feasibility, interpretability, and alignment with the needs of legal practitioners and decision-makers. We believe that our analysis can serve as a guideline for developers aiming to build effective decision-support systems for the legal domain, while fostering a deeper understanding of challenges and potential advancements by neuro-symbolic approaches in legal applications.

Recently, ABA Learning has been proposed as a form of symbolic machine learning for drawing Assumption-Based Argumentation frameworks from background knowledge and positive and negative examples. We propose a novel method for implementing ABA Learning using Answer Set Programming as a way to help guide Rote Learning and generalisation in ABA Learning.

ProbLog is a popular probabilistic logic programming language and tool, widely used for applications requiring to deal with inherent uncertainties in structured domains. In this paper we study some connections between ProbLog and a variant of another well-known formalism combining symbolic reasoning and reasoning under uncertainty, namely probabilistic argumentation. Specifically, we show that ProbLog is an instance of a form of Probabilistic Abstract Argumentation (PAA) under the constellation approach, which builds upon Assumption-Based Argumentation (ABA). The connections pave the way towards equipping ProbLog with a variety of alternative semantics, inherited from PAA/PABA, as well as obtaining novel argumentation semantics for PAA/PABA, leveraging on existing connections between ProbLog and argumentation. Moreover, the connections pave the way towards novel forms of argumentative explanations for ProbLog’s outputs.

Computational argumentation (CA) has emerged, in recent decades, as a powerful formalism for knowl- edge representation and reasoning in the presence of conflicting information, notably when reasoning non-monotonically with rules and exceptions. Much existing work in CA has focused, to date, on rea- soning with given argumentation frameworks (AFs) or, more recently, on using AFs, possibly automat- ically drawn from other systems, for supporting forms of XAI. In this short paper we focus instead on the problem of learning AFs from data, with a focus on neuro-symbolic approaches. Specifically, we overview existing forms of neuro-argumentative (machine) learning, resulting from a combination of neural machine learning mechanisms and argumentative (symbolic) reasoning. We include in our overview neuro-symbolic paradigms that integrate reasoners with a natural understanding in argumen- tative terms, notably those capturing forms of non-monotonic reasoning in logic programming. We also outline avenues and challenges for future work in this spectrum.

The pursuit of trust in and fairness of AI systems in order to enable human-centric goals has been gathering pace of late, often supported by the use of explanations for the outputs of these systems. Several properties of explanations have been highlighted as critical for achieving trustworthy and fair AI systems, but one that has thus far been overlooked is that of descriptive accuracy (DA), i.e., that the explanation contents are in correspondence with the internal working of the explained system. Indeed, the violation of this core property would lead to the paradoxical situation of systems producing explanations which are not suitably related to how the system actually works: clearly this may hinder user trust. Further, if explanations violate DA then they can be deceitful, resulting in an unfair behavior toward the users. Crucial as the DA property appears to be, it has been somehow overlooked in the XAI literature to date. To address this problem, we consider the questions of formalizing DA and of analyzing its satisfaction by explanation methods. We provide formal definitions of naive, structural and dialectical DA, using the family of probabilistic classifiers as the context for our analysis. We evaluate the satisfaction of our given notions of DA by several explanation methods, amounting to two popular feature-attribution methods from the literature, variants thereof and a novel form of explanation that we propose. We conduct experiments with a varied selection of concrete probabilistic classifiers and highlight the importance, with a user study, of our most demanding notion of dialectical DA, which our novel method satisfies by design and others may violate. We thus demonstrate how DA could be a critical component in achieving trustworthy and fair systems, in line with the principles of human-centric AI.

We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for mod-els’ outputs. The conceptualisation is based on reinterpreting properties of semantics of AFs as explanation moulds, which are means for characterising argumentative relations. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement in bipolar AFs, showing how the ex-tracted bipolar AFs may be used as relation-based explanations for the outputs of causal models. We then evaluate our method empirically when the causal models represent (Bayesian and neural network) machine learning models for classification. The results show advantages over a popular approach from the literature, both in highlighting specific relationships between feature and classification variables and in generating counterfactual explanations with respect to a commonly used metric.

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., Accepted for presentation at AAAI 2023. Contains appendix with proofs and additional details about experiments

Recent work on explainability raises the question of what different types of explanations actually mean. One idea is that explanations can reveal information about the behaviour of the model on a subset of the input space. When this way of interpreting explanations is thought as an interactive process, inferences from explanations can be seen as a form of reasoning. In the case of case-based reasoning with abstract argumentation (AA-CBR), previous work has used arbitrated dispute trees as a methodology for explanation. Those are dispute trees where nodes are seen as losing or winning depending on the outcome for the new case under consideration. In this work we show how arbitrated dispute trees can be readapted for different inputs, which allows a broader interpretation of them, capturing more of the input-output behaviour of the model. We show this readaptation is correct by construction, and thus the resulting reasoning based on this reuse is monotonic and thus necessarily a faithful explanation.

Explainable AI aims at making the decisions of autonomous systems human-understandable. Argumentation frameworks are a natural tool for this purpose. Among them, bipolar abstract argumentation frameworks seem well suited to explain the effect of features on a classification decision and their formal properties can potentially be used to derive formal guarantees for explanations. Two particular interesting properties are correctness (if the explanation says that X affects Y, then X affects Y ) and completeness (if X affects Y, then the explanation says that X affects Y ). The reinforcement property of bipolar argumentation frameworks has been used as a natural correctness counterpart in previous work. Applied to the classification context, it basically states that attacking features should decrease and supporting features should increase the confidence of a classifier. In this short discussion paper, we revisit this idea, discuss potential limitations when considering reinforcement without a corresponding completeness property and how these limitations can potentially be overcome.

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 {\Delta}-robustness, the first notion to formally and deterministically assess the robustness (to model changes) of CFXs for neural networks. 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., Comment: Accepted at AAAI 2023, camera-ready version

Schwannomas of the olfactory nerve are rare tumors: to the best of our knowledge, 56 cases have been previously reported. Here we describe a new patient presenting with an isolated olfactory schwannoma, highlighting the importance of multiple ancillary tests to approach the intracranial lesion of the anterior skull base, including electron microscopy. We also discuss the enigmatic origin of this entity, moving from the normal histology of the olfactory nerve compared to a peripheral nerve.

A user receiving an explanation for outcomes produced by an artificially intelligent system expects that it satisfies the key property of descriptive accuracy (DA), i.e. that the explanation contents are in correspondence with the internal working of the system. Crucial as this property appears to be, it has been somehow overlooked in the XAI literature to date. To address this problem, we consider the questions of formalising DA and of analysing its satisfaction by explanation methods. We provide formal definitions of naive, structural and dialectical DA, using the family of probabilistic classifiers as the context for our analysis. We evaluate the satisfaction of our given notions of DA by several explanation methods, amounting to two popular feature-attribution methods from the literature and a novel form of explanation that we propose and complement our analysis with experiments carried out on a varied selection of concrete probabilistic classifiers.

Counterfactual explanations (CEs) are an increasingly popular way of explaining machine learning classifiers. Predominantly, they amount to data instances pointing to potential changes to the inputs that would lead to alternative outputs. In this position paper we question the widespread assumption that CEs should always be data instances, and argue instead that in some cases they may be better understood in terms of special types of relations between input features and classification variables. We illustrate how a special type of these relations, amounting to critical influences, can characterise and guide the search for data instances deemed suitable as CEs. These relations also provide compact indications of which input features - rather than their specific values in data instances - have counterfactual value.

Deception is a core challenge for AI safety and we focus on the problem that AI agents might learn deceptive strategies in pursuit of their objectives. We define the incentives one agent has to signal to and deceive another agent. We present several examples of deceptive artificial agents and show that our definition has desirable properties.

Background: Traumatic hand and wrist amputations are rare but debilitating injuries. Surgical replantation of the hand provides a unique alternative to revision surgery but requires appropriate access to necessary medical resources. This study aims to understand the national practice of replantation of traumatic hand amputation and to determine whether disparities exist in accessing surgical treatment. Methods: International Classification of Diseases, 10th Revision codes for replantation and revision amputation surgeries were used to gather data from the National Inpatient Sample from 2016 to 2019. Summary statistics were calculated on demographic, hospital, and outcome variables, with subanalysis performed for effect on replantation and revision rates. Results: Seventy-two patients were identified. The average patient was 35 years old with a strong male predominance (90%). The racial distribution of the cohort roughly mirrored the demographic proportions of race in the US population. Fifteen (21%) patients underwent replantation. This rate was similar between sexes, races, and income brackets. Hand replantation was primarily performed at large bed size (87%), private not-for-profit (73%), and urban teaching hospitals (94%). The most common insurance status for these patients was private, followed by Medicaid, Medicare, and self-pay. Forty-seven patients underwent revision amputation (65%) with no association between demographic characteristics. The patients remained hospitalized for significantly longer periods ( P = .0188) and paid significantly more ( P = .0014) if replanted. The patients were most frequently discharged home (65%), followed by skilled nursing facilities (18%). Conclusion: This study describes the current state of hand amputation management and finds no evidence of sociodemographic factors influencing the surgical care provided.

In settings without well-defined goals, methods for reward learning allow reinforcement learning agents to infer goals from human feedback. Existing work has discussed the problem that such agents may manipulate humans, or the reward learning process, in order to gain higher reward. We introduce the neglected problem that, in multi-agent settings, agents may have incentives to manipulate one another’s reward functions in order to change each other’s behav- ioral policies. We focus on the setting with humans acting alongside assistive (artificial) agents who must learn the reward function by interacting with these humans. We propose a possible solution to manipulation of human feedback in this setting: the Shared Value Prior (SVP). The SVP equips agents with an assumption that the reward functions of all humans are similar. Given this assumption, the actions of any human provide information to an agent about its reward, and so the agent is incentivised to observe these actions rather than to manipulate them. We present an expository example in which the SVP prevents manipulation.

We introduce the Forecasting Argumentation Framework (FAF), a novel argumentation framework for forecasting informed by re- cent judgmental forecasting research. FAFs comprise update frame- works which empower (human or artificial) agents to argue over time with and about probability of scenarios, whilst flagging per- ceived irrationality in their behaviour with a view to improving their forecasting accuracy. FAFs include three argument types with future forecasts and aggregate the strength of these arguments to inform estimates of the likelihood of scenarios. We describe an implementation of FAFs for supporting forecasting agents.

In recent years, there have been many attempts to combine XAI with the field of symbolic AI in order to generate explanations for neural networks that are more interpretable and better align with human reasoning, with one prominent candidate for this synergy being the sub-field of computational argumentation. One method is to represent neural networks with quantitative bipolar argumentation frameworks (QBAFs) equipped with a particular semantics. The resulting QBAF can then be viewed as an explanation for the associated neural network. In this paper, we explore a novel LRP-based semantics under a new QBAF variant, namely neural QBAFs (nQBAFs). Since an nQBAF of a neural network is typically large, the nQBAF must be simplified before being used as an explanation. Our empirical evaluation indicates that the manner of this simplification is all important for the quality of the resulting explanation.