Deep learning-based expert models have reached superhuman performance in decision-making domains such as chess and Go. However, it is under-explored to explain or comment on given decisions although it is important for human education and model explainability. The outputs of expert models are accurate, but yet difficult to interpret for humans. On the other hand, large language models (LLMs) produce fluent commentary but are prone to hallucinations due to their limited decision-making capabilities. To bridge this gap between expert models and LLMs, we focus on chess commentary as a representative case of explaining complex decision-making processes through language and address both the generation and evaluation of commentary. We introduce Concept-guided Chess Commentary generation (CCC) for producing commentary and GPT-based Chess Commentary Evaluation (GCC-Eval) for assessing it. CCC integrates the decision-making strengths of expert models with the linguistic fluency of LLMs through prioritized, concept-based explanations. GCC-Eval leverages expert knowledge to evaluate chess commentary based on informativeness and linguistic quality. Experimental results, validated by both human judges and GCC-Eval, demonstrate that CCC generates commentary that is accurate, informative, and fluent.

We propose a novel approach that uses large language models (LLMs) to generate persona-driven conversations between Players and Non-Player Characters (NPC) in games. Showcasing the application of our methodology, we introduce the Minecraft Persona-driven Dialogue dataset (MCPDial). Starting with a small seed of expert-written conversations, we employ our method to generate hundreds of additional conversations. Each conversation in the dataset includes rich character descriptions of the player and NPC. The conversations are long, allowing for in-depth and extensive interactions between the player and NPC. MCPDial extends beyond basic conversations by incorporating canonical function calls (e.g. "Call find a resource on iron ore") between the utterances. Finally, we conduct a qualitative analysis of the dataset to assess its quality and characteristics.

In the current era of social media and generative AI, an ability to automatically assess the credibility of online social media content is of tremendous importance. Credibility assessment is fundamentally based on aggregating credibility signals, which refer to small units of information, such as content factuality, bias, or a presence of persuasion techniques, into an overall credibility score. Credibility signals provide a more granular, more easily explainable and widely utilizable information in contrast to currently predominant fake news detection, which utilizes various (mostly latent) features. A growing body of research on automatic credibility assessment and detection of credibility signals can be characterized as highly fragmented and lacking mutual interconnections. This issue is even more prominent due to a lack of an up-to-date overview of research works on automatic credibility assessment. In this survey, we provide such systematic and comprehensive literature review of 175 research papers while focusing on textual credibility signals and Natural Language Processing (NLP), which undergoes a significant advancement due to Large Language Models (LLMs). While positioning the NLP research into the context of other multidisciplinary research works, we tackle with approaches for credibility assessment as well as with 9 categories of credibility signals (we provide a thorough analysis for 3 of them, namely: 1) factuality, subjectivity and bias, 2) persuasion techniques and logical fallacies, and 3) claims and veracity). Following the description of the existing methods, datasets and tools, we identify future challenges and opportunities, while paying a specific attention to recent rapid development of generative AI.

Flashcard schedulers rely on 1) student models to predict the flashcards a student knows; and 2) teaching policies to pick which cards to show next via these predictions. Prior student models, however, just use study data like the student's past responses, ignoring the text on cards. We propose content-aware scheduling, the first schedulers exploiting flashcard content. To give the first evidence that such schedulers enhance student learning, we build KARL, a simple but effective content-aware student model employing deep knowledge tracing (DKT), retrieval, and BERT to predict student recall. We train KARL by collecting a new dataset of 123,143 study logs on diverse trivia questions. KARL bests existing student models in AUC and calibration error. To ensure our improved predictions lead to better student learning, we create a novel delta-based teaching policy to deploy KARL online. Based on 32 study paths from 27 users, KARL improves learning efficiency over SOTA, showing KARL's strength and encouraging researchers to look beyond historical study data to fully capture student abilities.

Designing optimization approaches, whether heuristic or meta-heuristic, usually demands extensive manual intervention and has difficulty generalizing across diverse problem domains. The combination of Large Language Models (LLMs) and Evolutionary Algorithms (EAs) offers a promising new approach to overcome these limitations and make optimization more automated. In this setup, LLMs act as dynamic agents that can generate, refine, and interpret optimization strategies, while EAs efficiently explore complex solution spaces through evolutionary operators. Since this synergy enables a more efficient and creative search process, we first conduct an extensive review of recent research on the application of LLMs in optimization. We focus on LLMs' dual functionality as solution generators and algorithm designers. Then, we summarize the common and valuable designs in existing work and propose a novel LLM-EA paradigm for automated optimization. Furthermore, centered on this paradigm, we conduct an in-depth analysis of innovative methods for three key components: individual representation, variation operators, and fitness evaluation. We address challenges related to heuristic generation and solution exploration, especially from the LLM prompts' perspective. Our systematic review and thorough analysis of the paradigm can assist researchers in better understanding the current research and promoting the development of combining LLMs with EAs for automated optimization.

Large Language Models (LLMs) have demonstrated the ability to adopt a personality and behave in a human-like manner. There is a large body of research that investigates the behavioural impacts of personality in less obvious areas such as investment attitudes or creative decision making. In this study, we investigated whether an LLM persona with a specific Big Five personality profile would perform an investment task similarly to a human with the same personality traits. We used a simulated investment task to determine if these results could be generalised into actual behaviours. In this simulated environment, our results show these personas produced meaningful behavioural differences in all assessed categories, with these behaviours generally being consistent with expectations derived from human research. We found that LLMs are able to generalise traits into expected behaviours in three areas: learning style, impulsivity and risk appetite while environmental attitudes could not be accurately represented. In addition, we showed that LLMs produce behaviour that is more reflective of human behaviour in a simulation environment compared to a survey environment.

The growing integration of digitized infrastructure with Internet of Things (IoT) networks has transformed the management and optimization of building energy consumption. By leveraging IoT-based monitoring systems, stakeholders such as building managers, energy suppliers, and policymakers can make data-driven decisions to improve energy efficiency. However, accurate energy forecasting and analytics face persistent challenges, primarily due to the inherent physical constraints of buildings and the diverse, heterogeneous nature of IoT-generated data. In this study, we conduct a comprehensive benchmarking of two publicly available IoT datasets, evaluating the performance of time series foundation models in the context of building energy analytics. Our analysis shows that single-modal models demonstrate significant promise in overcoming the complexities of data variability and physical limitations in buildings, with future work focusing on optimizing multi-modal models for sustainable energy management.

We consider Bayesian algorithm execution (BAX), a framework for efficiently selecting evaluation points of an expensive function to infer a property of interest encoded as the output of a base algorithm. Since the base algorithm typically requires more evaluations than are feasible, it cannot be directly applied. Instead, BAX methods sequentially select evaluation points using a probabilistic numerical approach. Current BAX methods use expected information gain to guide this selection. However, this approach is computationally intensive. Observing that, in many tasks, the property of interest corresponds to a target set of points defined by the function, we introduce PS-BAX, a simple, effective, and scalable BAX method based on posterior sampling. PS-BAX is applicable to a wide range of problems, including many optimization variants and level set estimation. Experiments across diverse tasks demonstrate that PS-BAX performs competitively with existing baselines while being significantly faster, simpler to implement, and easily parallelizable, setting a strong baseline for future research. Additionally, we establish conditions under which PS-BAX is asymptotically convergent, offering new insights into posterior sampling as an algorithm design paradigm.

Time series forecasting is a critical task in various domains, where accurate predictions can drive informed decision-making. Traditional forecasting methods often rely on current observations of variables to predict future outcomes, typically overlooking the influence of latent confounders, unobserved variables that simultaneously affect both the predictors and the target outcomes. This oversight can introduce bias and degrade the performance of predictive models. In this study, we address this challenge by proposing an enhanced forecasting approach that incorporates representations of latent confounders derived from historical data. By integrating these confounders into the predictive process, our method aims to improve the accuracy and robustness of time series forecasts. The proposed approach is demonstrated through its application to climate science data, showing significant improvements over traditional methods that do not account for confounders.

This study presents the ``Arabic Derivational ChainBank,'' a novel framework for modeling Arabic derivational morphology. It establishes connections between forms and meanings by constructing a chain of derived words that reflect their derivational significance. To expedite the process, a rule-based methodology was employed, avoiding time-consuming manual annotation. The derivational network was then aligned with the CamelMorph morphological analyzer database. This two-step process resulted in a chain of derived word lemmas linked to their roots, encompassing 23,333 evaluated derivational relations, thereby demonstrating the efficiency of the ChainBank.