Antonis Bikakis

JAIR Journal 2025 Journal Article

A Graphical Formalism for Reasoning about Substitution in Resource Transforming Procedures

• Antonis Bikakis
• Fabio Aurelio D'Asaro
• Aissatou Diallo
• Luke Dickens
• Anthony Hunter
• Rob Miller

The ability to repurpose and substitute materials and resources when necessary is an important aspect of human reasoning and activity. In particular, substitution plays a vital role in resource consuming and artifact producing activities – purposeful, goal directed procedures that transform resources from raw materials into finished products, the descriptions of which we refer to here as recipes. To see this, consider how adaptable humans are when we encounter constraints, such as limited resources, when making, manufacturing and constructing. In spite of this there has been comparatively little work given to developing representations for substitution within such contexts in a formal reasoning framework. We address this gap by proposing a graphical formalisation that captures consumables and the actions on them in the form of labelled bipartite graphs. Using examples such as “do it yourself" (DIY) instructions, manufacturing processes and cooking recipes to illustrate, we then propose formal definitions for comparing recipes, for composing recipes from subrecipes, and for deconstructing recipes into subrecipes. We then introduce and compare two formal definitions for substitution which are required when there are missing consumables, or some actions are not possible, or because there is some need to change the final product. We illustrate how automated reasoning about recipes in this context may be achieved by implementing our definitions in answer set programming (ASP).

AAAI Conference 2025 Conference Paper

Measuring Error Alignment for Decision-Making Systems

• Binxia Xu
• Antonis Bikakis
• Daniel F.O. Onah
• Andreas Vlachidis
• Luke Dickens

Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and alternative ways are needed to establish trust in those systems, and determine how well they align with human values. We argue that good measures of the information processing similarities between AI and humans, may be able to achieve these same ends. While Representational alignment (RA) approaches measure similarity between the internal states of two systems, the associated data can be expensive and difficult to collect for human systems. In contrast, Behavioural alignment (BA) comparisons are cheaper and easier, but questions remain as to their sensitivity and reliability. We propose two new behavioural alignment metrics misclassification agreement which measures the similarity between the errors of two systems on the same instances, and class-level error similarity which measures the similarity between the error distributions of two systems. We show that our metrics correlate well with RA metrics, and provide complementary information to another BA metric, within a range of domains, and set the scene for a new approach to value alignment.

ECAI Conference 2025 Conference Paper

RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation

• Aïssatou Diallo
• Antonis Bikakis
• Luke Dickens
• Anthony Hunter
• Rob Miller 0002

Commonsense reasoning is a key aspect of human intelligence. If we are to develop robust and deep intelligent systems, then we need to understand the diversity and complexity of commonsense reasoning across the gamut of human activities. An interesting class of commonsense reasoning problems arises when people are faced with natural disasters. To investigate this topic, we present RESPONSE, a human-curated dataset containing 1789 annotated instances featuring 6037 sets of questions designed to assess LLMs’ commonsense reasoning in disaster situations across different time frames. The dataset includes problem descriptions, missing resources, time-sensitive solutions, and their justifications, with a subset validated by environmental engineers. Through both automatic metrics and human evaluation, we compare LLM-generated recommendations against human responses. Our findings show that even state-of-the-art models like GPT-4 achieve only 37% human-evaluated correctness for immediate response actions, highlighting significant room for improvement in LLMs’ ability for commonsense reasoning in crises.

FLAP Journal 2025 Journal Article

Social Argumentation Systems

• Antonis Bikakis
• Giorgos Flouris
• Joao Leite
• Theodore Patkos

While a lot of research has been conducted on understanding and formalising the interplay of arguments within the context of Computational Argumentation, this research is not fully applicable to the types of arguments that populate the Social Web. In that context, arguments usually have the form of comments, opinions or reviews, and are the main ingredients of online discussion forums, social networks, online rating and review sites, debate portals and other online communities - the electronic version of word-of-mouth communication. As a result, voting and other forms of reaction to the provided comments or arguments (other than just “attacks”) are allowed, features that are not normally considered in the classical literature on Computational Argumentation. In this chapter, we study extensions of argumentation frameworks that have been proposed to describe and understand the more complex types of interactions among arguments that can be found in the Social Web, and present the current state-of-the-art, as well as open problems.

NeSy Conference 2024 Conference Paper

Context Helps: Integrating Context Information with Videos in a Graph-Based HAR Framework

• Binxia Xu
• Antonis Bikakis
• Daniel F. O. Onah
• Andreas Vlachidis
• Luke Dickens

Abstract Human Activity Recognition (HAR) from videos is a challenging, data intensive task. There have been significant strides in recent years, but even state-of-the-art (SoTA) models rely heavily on domain specific supervised fine-tuning of visual features, and even with this data- and compute-intensive fine-tuning, overall performance can still be limited. We argue that the next generation of HAR models could benefit from explicit neuro-symbolic mechanisms in order to flexibly exploit rich contextual information available in, and for, videos. With a view to this, we propose a Human Activity Recognition with Context Prompt (HARCP) task to investigate the value of contextual information for video-based HAR. We also present a neuro-symbolic graph neural network-based framework that integrates zero-shot object localisation to address the HARCP task. This captures the human activity as a sequence of graph-based scene representations relating parts of the human body to key objects, supporting the targeted injection of external contextual knowledge in symbolic form. We evaluate existing HAR baselines alongside our graph-based methods to demonstrate the advantage of being able to accommodate this additional channel of information. Our evaluations show that not only does context information from key objects boost accuracy beyond that provided by SoTA HAR models alone, there is also a greater semantic similarity between our model’s errors and the target class. We argue that this represents an improved model alignment with human-like errors and quantify this with a novel measure we call Semantic Prediction Dispersion.

IJCAI Conference 2021 Conference Paper

Abstract Argumentation Frameworks with Domain Assignments

• Alexandros Vassiliades
• Theodore Patkos
• Giorgos Flouris
• Antonis Bikakis
• Nick Bassiliades
• Dimitris Plexousakis

Argumentative discourse rarely consists of opinions whose claims apply universally. As with logical statements, an argument applies to specific objects in the universe or relations among them, and may have exceptions. In this paper, we propose an argumentation formalism that allows associating arguments with a domain of application. Appropriate semantics are given, which formalise the notion of partial argument acceptance, i. e. the set of objects or relations that an argument can be applied to. We show that our proposal is in fact equivalent to the standard Argumentation Frameworks of Dung, but allows a more intuitive and compact expression of some core concepts of commonsense and non-monotonic reasoning, such as the scope of an argument, exceptions, relevance and others.

FLAP Journal 2021 Journal Article

Joint Attacks and Accrual in Argumentation Frameworks.

• Antonis Bikakis
• Andrea Cohen
• Wolfgang Dvorák
• Giorgos Flouris
• Simon Parsons

AIJ Journal 2020 Journal Article

Probabilistic reasoning about epistemic action narratives

• Fabio Aurelio D'Asaro
• Antonis Bikakis
• Luke Dickens
• Rob Miller

We propose the action language EPEC – Epistemic Probabilistic Event Calculus – that supports probabilistic, epistemic reasoning about narratives of action occurrences and environmentally triggered events, and in particular facilitates reasoning about future belief-conditioned actions and their consequences in domains that include both perfect and imperfect sensing actions. To provide a declarative semantics for sensing and belief conditioned actions in a probabilistic, narrative setting we introduce the novel concept of an epistemic reduct. We then formally compare our language with two established frameworks for probabilistic reasoning about action – the action language PAL by Baral et al. , and the extension of the situation calculus to reason about noisy sensors and effectors by Bacchus et al. In both cases we prove a correspondence with EPEC for a class of domains representable in both frameworks.

KR Conference 2016 Short Paper

A Multi-Aspect Evaluation Framework for Comments on the Social Web

• Theodore Patkos
• Antonis Bikakis
• Giorgos Flouris

Users’ reviews, comments and votes on the Social Web form the modern version of word-of-mouth communication, which has a huge impact on people’s habits and businesses. Nonetheless, there are only few attempts to formally model and analyze them using Computational Models of Argument, which achieved a first significant step in bringing these two fields closer. In this paper, we attempt their further integration by formalizing standard features of the Social Web, such as commentary and social voting, and by proposing methods for the evaluation of the comments’ quality and acceptance.

ECAI Conference 2016 Conference Paper

Symmetric Multi-Aspect Evaluation of Comments - Extended Abstract

• Theodore Patkos
• Giorgos Flouris
• Antonis Bikakis

EUMAS Conference 2014 Conference Paper

Computing Coalitions in Multiagent Systems: A Contextual Reasoning Approach

• Antonis Bikakis
• Patrice Caire

Abstract In multiagent systems, agents often have to rely on other agents to reach their goals, for example when they lack a needed resource or do not have the capability to perform a required action. Agents therefore need to cooperate. Some of the questions then raised, such as, which agent to cooperate with, are addressed in the field of coalition formation. In this paper we go further and first, address the question of how to compute the solution space for the formation of coalitions using a contextual reasoning approach. We model agents as contexts in Multi-Context Systems (MCS) and dependence relations among agents as bridge rules. We then systematically compute all potential coalitions using algorithms for MCS equilibria. Finally, given a set of functional and non-functional requirements, we propose ways to select the best solutions. We illustrate our approach with an example from robotics.

FLAP Journal 2014 Journal Article

Tools for Conviviality in Multi-Context Systems.

• Antonis Bikakis
• Patrice Caire
• Yves Le Traon

A common feature of many distributed systems, including web social networks, peer-to-peer systems and Ambient Intelligence systems, is cooperation in terms of information exchange among heterogeneous entities. In order to facilitate the exchange of information, we first need ways to evaluate it. The concept of conviviality was recently proposed for modeling and measuring cooperation among agents in multiagent systems. In this paper, we introduce conviviality as a property of Multi-Context Systems (MCS). We first present how to use conviviality to model and evaluate interactions among different contexts, which represent heterogeneous entities in a distributed system. Then, as one cause of logical conflicts in MCS is due to the exchange of information between mutually inconsistent contexts, we show how inconsistency can be resolved using the conviviality property. We illustrate our work with an example from web social networks.

KR Conference 2010 Conference Paper

Reasoning about Context in Ambient Intelligence Environments: A Report from the Field

• Grigoris Antoniou
• Constantinos Papatheodorou
• Antonis Bikakis

AAAI Conference 2008 Short Paper

Distributed Reasoning with Conflicts in a Multi-Context Framework

• Antonis Bikakis

AAAI Conference 2005 Short Paper

DR-Prolog:A System for Reasoning with Rules and Ontologies on the Semantic Web

• Antonis Bikakis

Defeasible reasoning is a rule-based approach for efficient reasoning with incomplete and inconsis-tent information. Such reasoning is, among others, useful for ontology integration, where conflicting information arises naturally; and for the modeling of business rules and policies, where rules with ex-ceptions are often used. This paper describes these scenarios in more detail, and reports on the imple-mentation of a system for defeasible reasoning on the Web. The system (a) is syntactically compati-ble with RuleML; (b) features strict and defeasible rules, priorities and two kinds of negation; (c) is based on a translation to logic programming with declarative semantics; (d) is flexible and adaptable to different intuitions within defeasible reasoning; and (e) can reason with rules, RDF, RDF Schema and (parts of) OWL ontologies.