The rapid development of Large Language Models (LLMs) like GPT-4, Claude-3, and Gemini has transformed the field of natural language processing. However, it has also resulted in a significant issue known as Benchmark Data Contamination (BDC). This occurs when language models inadvertently incorporate evaluation benchmark information from their training data, leading to inaccurate or unreliable performance during the evaluation phase of the process. This paper reviews the complex challenge of BDC in LLM evaluation and explores alternative assessment methods to mitigate the risks associated with traditional benchmarks. The paper also examines challenges and future directions in mitigating BDC risks, highlighting the complexity of the issue and the need for innovative solutions to ensure the reliability of LLM evaluation in real-world applications.

The increasing availability of digital collections of historical and contemporary literature presents a wealth of possibilities for new research in the humanities. The scale and diversity of such collections however, presents particular challenges in identifying and extracting relevant content. This paper presents Curatr, an online platform for the exploration and curation of literature with machine learning-supported semantic search, designed within the context of digital humanities scholarship. The platform provides a text mining workflow that combines neural word embeddings with expert domain knowledge to enable the generation of thematic lexicons, allowing researches to curate relevant sub-corpora from a large corpus of 18th and 19th century digitised texts.

Counterfactual explanations have emerged as a popular solution for the eXplainable AI (XAI) problem of elucidating the predictions of black-box deep-learning systems due to their psychological validity, flexibility across problem domains and proposed legal compliance. While over 100 counterfactual methods exist, claiming to generate plausible explanations akin to those preferred by people, few have actually been tested on users ($\sim7\%$). So, the psychological validity of these counterfactual algorithms for effective XAI for image data is not established. This issue is addressed here using a novel methodology that (i) gathers ground truth human-generated counterfactual explanations for misclassified images, in two user studies and, then, (ii) compares these human-generated ground-truth explanations to computationally-generated explanations for the same misclassifications. Results indicate that humans do not "minimally edit" images when generating counterfactual explanations. Instead, they make larger, "meaningful" edits that better approximate prototypes in the counterfactual class.

Many recent deep learning-based solutions have widely adopted the attention-based mechanism in various tasks of the NLP discipline. However, the inherent characteristics of deep learning models and the flexibility of the attention mechanism increase the models' complexity, thus leading to challenges in model explainability. In this paper, to address this challenge, we propose a novel practical framework by utilizing a two-tier attention architecture to decouple the complexity of explanation and the decision-making process. We apply it in the context of a news article classification task. The experiments on two large-scaled news corpora demonstrate that the proposed model can achieve competitive performance with many state-of-the-art alternatives and illustrate its appropriateness from an explainability perspective.

Whilst an abundance of techniques have recently been proposed to generate counterfactual explanations for the predictions of opaque black-box systems, markedly less attention has been paid to exploring the uncertainty of these generated explanations. This becomes a critical issue in high-stakes scenarios, where uncertain and misleading explanations could have dire consequences (e.g., medical diagnosis and treatment planning). Moreover, it is often difficult to determine if the generated explanations are well grounded in the training data and sensitive to distributional shifts. This paper proposes several practical solutions that can be leveraged to solve these problems by establishing novel connections with other research works in explainability (e.g., trust scores) and uncertainty estimation (e.g., Monte Carlo Dropout). Two experiments demonstrate the utility of our proposed solutions.

Recently, it has been proposed that fruitful synergies may exist between Deep Learning (DL) and Case Based Reasoning (CBR); that there are insights to be gained by applying CBR ideas to problems in DL (what could be called DeepCBR). In this paper, we report on a program of research that applies CBR solutions to the problem of Explainable AI (XAI) in the DL. We describe a series of twin-systems pairings of opaque DL models with transparent CBR models that allow the latter to explain the former using factual, counterfactual and semi-factual explanation strategies. This twinning shows that functional abstractions of DL (e.g., feature weights, feature importance and decision boundaries) can be used to drive these explanatory solutions. We also raise the prospect that this research also applies to the problem of Data Augmentation in DL, underscoring the fecundity of these DeepCBR ideas.

In recent years there has been a cascade of research in attempting to make AI systems more interpretable by providing explanations; so-called Explainable AI (XAI). Most of this research has dealt with the challenges that arise in explaining black-box deep learning systems in classification and regression tasks, with a focus on tabular and image data; for example, there is a rich seam of work on post-hoc counterfactual explanations for a variety of black-box classifiers (e.g., when a user is refused a loan, the counterfactual explanation tells the user about the conditions under which they would get the loan). However, less attention has been paid to the parallel interpretability challenges arising in AI systems dealing with time series data. This paper advances a novel technique, called Native-Guide, for the generation of proximal and plausible counterfactual explanations for instance-based time series classification tasks (e.g., where users are provided with alternative time series to explain how a classification might change). The Native-Guide method retrieves and uses native in-sample counterfactuals that already exist in the training data as "guides" for perturbation in time series counterfactual generation. This method can be coupled with both Euclidean and Dynamic Time Warping (DTW) distance measures. After illustrating the technique on a case study involving a climate classification task, we reported on a comprehensive series of experiments on both real-world and synthetic data sets from the UCR archive. These experiments provide computational evidence of the quality of the counterfactual explanations generated.

Topic models can provide us with an insight into the underlying latent structure of a large corpus of documents. A range of methods have been proposed in the literature, including probabilistic topic models and techniques based on matrix factorization. However, in both cases, standard implementations rely on stochastic elements in their initialization phase, which can potentially lead to different results being generated on the same corpus when using the same parameter values. This corresponds to the concept of "instability" which has previously been studied in the context of $k$-means clustering. In many applications of topic modeling, this problem of instability is not considered and topic models are treated as being definitive, even though the results may change considerably if the initialization process is altered. In this paper we demonstrate the inherent instability of popular topic modeling approaches, using a number of new measures to assess stability. To address this issue in the context of matrix factorization for topic modeling, we propose the use of ensemble learning strategies. Based on experiments performed on annotated text corpora, we show that a K-Fold ensemble strategy, combining both ensembles and structured initialization, can significantly reduce instability, while simultaneously yielding more accurate topic models.

Twitter introduced user lists in late 2009, allowing users to be grouped according to meaningful topics or themes. Lists have since been adopted by media outlets as a means of organising content around news stories. Thus the curation of these lists is important - they should contain the key information gatekeepers and present a balanced perspective on a story. Here we address this list curation process from a recommender systems perspective. We propose a variety of criteria for generating user list recommendations, based on content analysis, network analysis, and the "crowdsourcing" of existing user lists. We demonstrate that these types of criteria are often only successful for datasets with certain characteristics. To resolve this issue, we propose the aggregation of these different "views" of a news story on Twitter to produce more accurate user recommendations to support the curation process.

Current approaches for word-sense disambiguation (WSD) try to relate the senses of the target words by optimizing a score for each sense in the context of all other words' senses. However, by scoring each sense separately, they often fail to optimize the relations between the resulting senses. We address this problem by proposing a HITS-inspired method that attempts to optimize the score for the entire sense combination rather than one-word-at-a-time. We also exploit word-sense disambiguation via topic-models, when retrieving senses from heterogeneous sense inventories. Although this entails the relaxation of several assumptions behind current WSD algorithms, we show that our proposed method E-WSD achieves better results than current state-of-the-art approaches, without the need for additional background knowledge.