Search

Explainable AI (XAI) can greatly enhance user trust and satisfaction in AI-assisted decision-making processes. Recent findings suggest that a single explainer may not meet the diverse needs of multiple users in an AI system; indeed, even individual users may require multiple explanations. This highlights the necessity for a "multi-shot" approach, employing a combination of explainers to form what we introduce as an "explanation strategy". Tailored to a specific user or a user group, an "explanation experience" describes interactions with personalised strategies designed to enhance their AI decision-making processes. The iSee platform is designed for the intelligent sharing and reuse of explanation experiences, using Case-based Reasoning to advance best practices in XAI. The platform provides tools that enable AI system designers, i.e. design users, to design and iteratively revise the most suitable explanation strategy for their AI system to satisfy end-user needs. All knowledge generated within the iSee platform is formalised by the iSee ontology for interoperability. We use a summative mixed methods study protocol to evaluate the usability and utility of the iSee platform with six design users across varying levels of AI and XAI expertise. Our findings confirm that the iSee platform effectively generalises across applications and its potential to promote the adoption of XAI best practices., Comment: Accepted to appear at the ECAI-PAIS 2024 main conference proceedings

Explainable Artificial Intelligence (XAI) aims to improve the transparency of autonomous decision-making through explanations. Recent literature has emphasised users' need for holistic "multi-shot" explanations and the ability to personalise their engagement with XAI systems. We refer to this user-centred interaction as an XAI Experience. Despite advances in creating XAI experiences, evaluating them in a user-centred manner has remained challenging. To address this, we introduce the XAI Experience Quality (XEQ) Scale (pronounced "Seek" Scale), for evaluating the user-centred quality of XAI experiences. Furthermore, XEQ quantifies the quality of experiences across four evaluation dimensions: learning, utility, fulfilment and engagement. These contributions extend the state-of-the-art of XAI evaluation, moving beyond the one-dimensional metrics frequently developed to assess single-shot explanations. In this paper, we present the XEQ scale development and validation process, including content validation with XAI experts as well as discriminant and construct validation through a large-scale pilot study. Out pilot study results offer strong evidence that establishes the XEQ Scale as a comprehensive framework for evaluating user-centred XAI experiences.

The evolution of Explainable Artificial Intelligence (XAI) has emphasised the significance of meeting diverse user needs. The approaches to identifying and addressing these needs must also advance, recognising that explanation experiences are subjective, user-centred processes that interact with users towards a better understanding of AI decision-making. This paper delves into the interrelations in multi-faceted XAI and examines how different types of explanations collaboratively meet users' XAI needs. We introduce the Intent Fulfilment Framework (IFF) for creating explanation experiences. The novelty of this paper lies in recognising the importance of "follow-up" on explanations for obtaining clarity, verification and/or substitution. Moreover, the Explanation Experience Dialogue Model integrates the IFF and "Explanation Followups" to provide users with a conversational interface for exploring their explanation needs, thereby creating explanation experiences. Quantitative and qualitative findings from our comparative user study demonstrate the impact of the IFF in improving user engagement, the utility of the AI system and the overall user experience. Overall, we reinforce the principle that "one explanation does not fit all" to create explanation experiences that guide the complex interaction through conversation.

Retrieval-Augmented Generation (RAG) enhances Large Language Model (LLM) output by providing prior knowledge as context to input. This is beneficial for knowledge-intensive and expert reliant tasks, including legal question-answering, which require evidence to validate generated text outputs. We highlight that Case-Based Reasoning (CBR) presents key opportunities to structure retrieval as part of the RAG process in an LLM. We introduce CBR-RAG, where CBR cycle's initial retrieval stage, its indexing vocabulary, and similarity knowledge containers are used to enhance LLM queries with contextually relevant cases. This integration augments the original LLM query, providing a richer prompt. We present an evaluation of CBR-RAG, and examine different representations (i.e. general and domain-specific embeddings) and methods of comparison (i.e. inter, intra and hybrid similarity) on the task of legal question-answering. Our results indicate that the context provided by CBR's case reuse enforces similarity between relevant components of the questions and the evidence base leading to significant improvements in the quality of generated answers., Comment: Submitted to ICCBR'24

Multi-node optical clock networks will enable future studies of fundamental physics and enable applications in quantum and classical communications as well as navigation and geodesy. We implement the first ever multi-node optical clock network with real-time, relative synchronization over free-space communication channels and precision on the order of 10 fs, realized as a three-node system in a hub-and-spoke topology. In this paper we describe the system and its performance, including a new, independent, out-of-loop verification of two-way optical time synchronization.

Good communication is critical to good healthcare. Clinical dialogue is a conversation between health practitioners and their patients, with the explicit goal of obtaining and sharing medical information. This information contributes to medical decision-making regarding the patient and plays a crucial role in their healthcare journey. The reliance on note taking and manual scribing processes are extremely inefficient and leads to manual transcription errors when digitizing notes. Automatic Speech Recognition (ASR) plays a significant role in speech-to-text applications, and can be directly used as a text generator in conversational applications. However, recording clinical dialogue presents a number of general and domain-specific challenges. In this paper, we present a seq2seq learning approach for ASR transcription error correction of clinical dialogues. We introduce a new Gastrointestinal Clinical Dialogue (GCD) Dataset which was gathered by healthcare professionals from a NHS Inflammatory Bowel Disease clinic and use this in a comparative study with four commercial ASR systems. Using self-supervision strategies, we fine-tune a seq2seq model on a mask-filling task using a domain-specific PubMed dataset which we have shared publicly for future research. The BART model fine-tuned for mask-filling was able to correct transcription errors and achieve lower word error rates for three out of four commercial ASR outputs., Comment: Pre-print of the paper accepted at the 6th International Workshop on Health Intelligence (W3PHIAI-22)

Counterfactual explanations focus on "actionable knowledge" to help end-users understand how a machine learning outcome could be changed to a more desirable outcome. For this purpose a counterfactual explainer needs to discover input dependencies that relate to outcome changes. Identifying the minimum subset of feature changes needed to action an output change in the decision is an interesting challenge for counterfactual explainers. The DisCERN algorithm introduced in this paper is a case-based counter-factual explainer. Here counterfactuals are formed by replacing feature values from a nearest unlike neighbour (NUN) until an actionable change is observed. We show how widely adopted feature relevance-based explainers (i.e. LIME, SHAP), can inform DisCERN to identify the minimum subset of "actionable features". We demonstrate our DisCERN algorithm on five datasets in a comparative study with the widely used optimisation-based counterfactual approach DiCE. Our results demonstrate that DisCERN is an effective strategy to minimise actionable changes necessary to create good counterfactual explanations., Comment: Pre-print of the paper accepted at the 33rd IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

Delivery of digital behaviour change interventions which encourage physical activity has been tried in many forms. Most often interventions are delivered as text notifications, but these do not promote interaction. Advances in conversational AI have improved natural language understanding and generation, allowing AI chatbots to provide an engaging experience with the user. For this reason, chatbots have recently been seen in healthcare delivering digital interventions through free text or choice selection. In this work, we explore the use of voice-based AI chatbots as a novel mode of intervention delivery, specifically targeting older adults to encourage physical activity. We co-created "FitChat", an AI chatbot, with older adults and we evaluate the first prototype using Think Aloud Sessions. Our thematic evaluation suggests that older adults prefer voice-based chat over text notifications or free text entry and that voice is a powerful mode for encouraging motivation.

Web servers are a popular target for adversaries as they are publicly accessible and often vulnerable to compromise. Compromises can go unnoticed for months, if not years, and recovery often involves a complete system rebuild. In this paper, we propose n-m-Variant Systems, an adversarial-resistant software rejuvenation framework for cloud-based web applications. We improve the state-of-the-art by introducing a variable m that provides a knob for administrators to tune an environment to balance resource usage, performance overhead, and security guarantees. Using m, security guarantees can be tuned for seconds, minutes, days, or complete resistance. We design and implement an n-m-Variant System prototype to protect a Mediawiki PHP application serving dynamic content from an external SQL persistent storage. Our performance evaluation shows a throughput reduction of 65% for 108 seconds of resistance and 83% for 12 days of resistance to sophisticated adversaries, given appropriate resource allocation. Furthermore, we use theoretical analysis and simulation to characterize the impact of system parameters on resilience to adversaries. Through these efforts, our work demonstrates how properties of cloud-based servers can enhance the integrity of Web servers.

The $5S_{1/2}\rightarrow 5D_{5/2}$ two-photon transition in Rb is of interest for the development of a compact optical atomic clock. Here we present a rigorous calculation of the 778.1~nm ac-Stark shift ($2.30(4) \times10^{-13}$(mW/mm$^2$)$^{-1}$) that is in good agreement with our measured value of $2.5(2) \times10^{-13}$(mW/mm$^2$)$^{-1}$. We include a calculation of the temperature-dependent blackbody radiation shift, we predict that the clock could be operated either with zero net BBR shift ($T=495.9(27)$~K) or with zero first-order sensitivity ($T=368.1(14)$~K). Also described is the calculation of the dc-Stark shift of 5.5(1)$\times 10^{-15}$/(V/cm$^2$) as well as clock sensitivities to optical alignment variations in both a cat's eye and flat mirror retro-reflector. Finally, we characterize these Stark effects discussing mitigation techniques necessary to reduce final clock instabilities., Comment: 12 pages, 7 figures, accepted for publication in Physical Review A

Extra-laboratory atomic clocks are necessary for a wide array of applications (e.g. satellite-based navigation and communication). Building upon existing vapor cell and laser technologies, we describe an optical atomic clock, designed around a simple and manufacturable architecture, that utilizes the 778~nm two-photon transition in rubidium and yields fractional frequency instabilities of $3\times10^{-13}/\sqrt{\tau (s)}$ for $\tau$ from 1~s to 10000~s. We present a complete stability budget for this system and explore the required conditions under which a fractional frequency instability of $1\times 10^{-15}$ can be maintained on long timescales. We provide precise characterization of the leading sensitivities to external processes including magnetic fields and fluctuations of the vapor cell temperature and 778~nm laser power. The system is constructed primarily from commercially-available components, an attractive feature from the standpoint of commercialization and deployment of optical frequency standards., Comment: 9 pages, 6 figures

We address a question of Cavenagh and Wanless asking: which finite abelian groups arise as the canonical group of a spherical latin bitrade? We prove the existence of an infinite family of finite abelian groups that do not arise as canonical groups of spherical latin bitrades. Using a connection between abelian sandpile groups of digraphs underlying directed Eulerian spherical embeddings, we go on to provide several, general, families of finite abelian groups that do arise as canonical groups. These families include: any abelian group in which each component of the Smith Normal Form has composite order; any abelian group with Smith Normal Form $\mathbb{Z}^{n}_p\oplus\left(\bigoplus_{i=1}^k\mathbb{Z}_{pa_i}\right)$, where $1\leq k$, $2\leq a_1,a_2,\ldots, a_k,p$ and $n\leq 1+2\sum_{i=1}^k(a_i - 1)$; and with one exception and three potential exceptions any abelian group of rank two.