Large Language Models (LLMs) such as GPT -5, GEMINI, Claude, and LLaMA have become foundational tools in artificial intelligence (AI), achieving state-of-the-art performance in summarization, translation, reasoning, and dialogue. However, since LLMs are increasingly integrated in high-risk decision making in domains such as healthcare, law, and education, their lack of transparency raises urgent concerns for safety, accountability, and public trust [12]. The scale and complexity of these models, covering billions of parameters trained in opaque corpora, make their internal reasoning fundamentally inscrutable. This opacity creates barriers to responsible adoption, as users often lack meaningful ways to understand or challenge outputs. Without stakeholder-sensitive explanations, systems risk overtrust, misinterpretation, or outright rejection [11]. Explainable AI (XAI) for LLMs has therefore evolved beyond technical introspection [6]. The goal is not only to expose internal mechanisms but also to support human interaction, trust calibration, and decision assurance. As model behavior becomes more emergent and unpredictable [10], explanation systems must serve cognitive, functional, and ethical purposes simultaneously [7].

Large Language Models (LLMs) are now increasingly widely used to simulate personas in virtual environments, leveraging their instruction-following capability. However, we discovered that even state-of-the-art LLMs cannot simulate personas with reversed performance (e.g., student personas with low proficiency in educational settings), which impairs the simulation diversity and limits the practical applications of the simulated environments. In this work, using mathematical reasoning as a representative scenario, we propose the first benchmark dataset for evaluating LLMs on simulating personas with reversed performance, a capability that we dub "counterfactual instruction following". We evaluate both open-weight and closed-source LLMs on this task and find that LLMs, including the OpenAI o1 reasoning model, all struggle to follow counterfactual instructions for simulating reversedly performing personas. Intersectionally simulating both the performance level and the race population of a persona worsens the effect even further. These results highlight the challenges of counterfactual instruction following and the need for further research.

The controllability of Large Language Models (LLMs) when used as conversational agents is a key challenge, particularly to ensure predictable and user-personalized responses. This work proposes an ontology-based approach to formally define conversational features that are typically qualitative in nature. By leveraging a set of linguistic descriptors, we derive quantitative definitions for qualitatively-defined concepts, enabling their integration into an ontology for reasoning and consistency checking. We apply this framework to the task of proficiency-level control in conversations, using CEFR language proficiency levels as a case study. These definitions are then formalized in description logic and incorporated into an ontology, which guides controlled text generation of an LLM through fine-tuning. Experimental results demonstrate that our approach provides consistent and explainable proficiency-level definitions, improving transparency in conversational AI.

ABSTRACT Spoken Language Understanding (SLU) is a core component of conversational systems, enabling machines to interpret user utterances. Despite its importance, developing effective SLU systems remains challenging due to the scarcity of labeled training data and the computational burden of deploying Large Language Models (LLMs) in real-world applications. To further alleviate these issues, we propose an Adaptive Feature Distillation framework that transfers rich semantic representations from a General Text Embed-dings (GTE)-based teacher model to a lightweight student model. Our method introduces a dynamic adapter equipped with a Residual Projection Neural Network (RPNN) to align heterogeneous feature spaces, and a Dynamic Distillation Coefficient (DDC) that adaptively modulates the distillation strength based on real-time feedback from intent and slot prediction performance. Experiments on the Chinese profile-based ProSLU benchmark demonstrate that AFD-SLU achieves state-of-the-art results, with 95.67% intent accuracy, 92.02% slot F1 score, and 85.50% overall accuracy.

Descriptions of complex nominal or verbal systems make use of inflectional classes. Inflectional classes bring together nouns which have similar stem changes and use similar exponents in their paradigms. Although inflectional classes can be very useful for language teaching as well as for setting up finite state morphological systems, it is unclear whether inflectional classes are cognitively real, in the sense that native speakers would need to discover these classes in order to learn how to properly inflect the nouns of their language. This study investigates whether the Discriminative Lexicon Model (DLM) can understand and produce Finnish inflected nouns without setting up inflectional classes, using a dataset with 55,271 inflected nouns of 2000 high-frequency Finnish nouns from 49 inflectional classes. Several DLM comprehension and production models were set up. Some models were not informed about frequency of use, and provide insight into learnability with infinite exposure (endstate learning). Other models were set up from a usage based perspective, and were trained with token frequencies being taken into consideration (frequency-informed learning). On training data, models performed with very high accuracies. For held-out test data, accuracies decreased, as expected, but remained acceptable. Across most models, performance increased for inflectional classes with more types, more lower-frequency words, and more hapax legomena, mirroring the productivity of the inflectional classes. The model struggles more with novel forms of unproductive and less productive classes, and performs far better for unseen forms belonging to productive classes. However, for usage-based production models, frequency was the dominant predictor of model performance, and correlations with measures of productivity were tenuous or absent.

From the dawn of the computer, Allen Turing dreamed of a robot that could communicate using language as a human being. The recent advances in the field of Large Language Models (LLMs) shocked the scientific community when a single model can apply for various natural language processing (NLP) tasks, while the output results are sometimes even better than most human communication skills. Models such as GPT, Claude, Grok, etc. have left their mark on the scientific community. However, it is unclear how much these models understand what they produce, especially in a nuanced theme such as humor. The question of whether computers understand humor is still open (among the decoders, the latest to be checked was GPT-2). We addressed this issue in this paper; we have showed that a fine-tuned decoder (GPT-4o) performed (Mean F1-macro score of 0.85) as well as the best fine-tuned encoder (RoBERTa with a Mean of F1-score 0.86)

Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but it has not been evaluated whether the learned units capture spurious correlations that hinder out-of-vocabulary performance. This work investigates two phonological inductive biases: Parameter Disentanglement, an architectural bias, and Phonological Semi-Supervision, a regularization technique, to improve isolated sign recognition of known signs and reconstruction quality of unseen signs with a vector-quantized autoencoder. The primary finding is that the learned representations from the proposed model are more effective for one-shot reconstruction of unseen signs and more discriminative for sign identification compared to a controlled baseline. This work provides a quantitative analysis of how explicit, linguistically-motivated biases can improve the generalization of learned representations of sign language.

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems and undermine trust. We argue that language models hallucinate because the training and evaluation procedures reward guessing over acknowledging uncertainty, and we analyze the statistical causes of hallucinations in the modern training pipeline. Hallucinations need not be mysterious -- they originate simply as errors in binary classification. If incorrect statements cannot be distinguished from facts, then hallucinations in pretrained language models will arise through natural statistical pressures. We then argue that hallucinations persist due to the way most evaluations are graded -- language models are optimized to be good test-takers, and guessing when uncertain improves test performance. This "epidemic" of penalizing uncertain responses can only be addressed through a socio-technical mitigation: modifying the scoring of existing benchmarks that are misaligned but dominate leaderboards, rather than introducing additional hallucination evaluations. This change may steer the field toward more trustworthy AI systems.

The rapid advancement of large language models presents significant opportunities for financial applications, yet systematic evaluation in specialized financial contexts remains limited. This study presents the first comprehensive evaluation of state-of-the-art LLMs using 1,560 multiple-choice questions from official mock exams across Levels I-III of CFA, most rigorous professional certifications globally that mirror real-world financial analysis complexity. We compare models distinguished by core design priorities: multi-modal and computationally powerful, reasoning-specialized and highly accurate, and lightweight efficiency-optimized. We assess models under zero-shot prompting and through a novel Retrieval-Augmented Generation pipeline that integrates official CFA curriculum content. The RAG system achieves precise domain-specific knowledge retrieval through hierarchical knowledge organization and structured query generation, significantly enhancing reasoning accuracy in professional financial certification evaluation. Results reveal that reasoning-oriented models consistently outperform others in zero-shot settings, while the RAG pipeline provides substantial improvements particularly for complex scenarios. Comprehensive error analysis identifies knowledge gaps as the primary failure mode, with minimal impact from text readability. These findings provide actionable insights for LLM deployment in finance, offering practitioners evidence-based guidance for model selection and cost-performance optimization.

Personality prediction from social media posts is a critical task that implies diverse applications in psychology and sociology. The Myers Briggs Type Indicator (MBTI), a popular personality inventory, has been traditionally predicted by machine learning (ML) and deep learning (DL) techniques. Recently, the success of Large Language Models (LLMs) has revealed their huge potential in understanding and inferring personality traits from social media content. However, directly exploiting LLMs for MBTI prediction faces two key challenges: the hallucination problem inherent in LLMs and the naturally imbalanced distribution of MBTI types in the population. In this paper, we propose PostToPersonality (PtoP), a novel LLM based framework for MBTI prediction from social media posts of individuals. Specifically, PtoP leverages Retrieval Augmented Generation with in context learning to mitigate hallucination in LLMs. Furthermore, we fine tune a pretrained LLM to improve model specification in MBTI understanding with synthetic minority oversampling, which balances the class imbalance by generating synthetic samples. Experiments conducted on a real world social media dataset demonstrate that PtoP achieves state of the art performance compared with 10 ML and DL baselines.