ABSTRACT Design/methodology/approach This study proposes a cognitive benchmarking framework to evaluate how large language models (LLMs) process and apply culturally specific knowledge. The framework integrates Bloom's Taxonomy with Retrieval - Augmented Generation (RAG) to assess model perform ance across six hierarchical cognitive domains: Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating. Using a curated Taiwanese Hakka digital cultural archive as the primary testbed, the evaluation measures LLM - generated responses' sem antic accuracy and cultural relevance. Purpose This research evaluates how effectively LLMs represent and generate minority cultural knowledge, specifically Taiwanese Hakka culture. To address this, the study proposes a structured and replicable evaluation framework integrating Bloom's Taxonomy and RAG . The research is guided by the following questions: (1) How do LLMs perform across different cognitive domains when processing Hakka ...

In this work, we investigate the use of Large Language Models (LLMs) within a graph-based Retrieval Augmented Generation (RAG) architecture for Energy Efficiency (EE) Question Answering. First, the system automatically extracts a Knowledge Graph (KG) from guidance and regulatory documents in the energy field. Then, the generated graph is navigated and reasoned upon to provide users with accurate answers in multiple languages. We implement a human-based validation using the RAGAs framework properties, a validation dataset comprising 101 question-answer pairs, and domain experts. Results confirm the potential of this architecture and identify its strengths and weaknesses. Validation results show how the system correctly answers in about three out of four of the cases (75.2 +- 2.7%), with higher results on questions related to more general EE answers (up to 81.0 +- 4.1%), and featuring promising multilingual abilities (4.4% accuracy loss due to translation).

Graph Chain-of-Thought (Graph-CoT) enables large language models (LLMs) to perform step-by-step reasoning over graph-structured knowledge, but existing pipelines suffer from low accuracy, excessive token usage, high latency, and low throughput due to single-agent monolithic prompts, repeated context re-encoding, and inefficient serving execution. We present GLM, the first multi-agent Graph-CoT system co-designed with an optimized LLM serving architecture. GLM decomposes reasoning into specialized agents for classification, reasoning, action generation, and graph retrieval, enabling branching and selective context sharing to reduce prompt length and reasoning iterations while preserving reasoning quality, thereby improving accuracy and reducing overall token consumption. To scale inference, we introduce a Graph-CoT-aware LLM inference mechanism with graph-specific KV-cache management, priority-based eviction, and pipelined execution to improve serving efficiency. Experiments demonstrate that GLM improves answer accuracy by up to 38%, reduces token cost by up to 95.7%, lowers inference latency by 90.3%, and achieves up to 15.1x higher throughput compared to state-of-the-art Graph-CoT baselines, enabling efficient adoption for complex real-world reasoning at scale.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding.

Linguistic errors are not merely deviations from normative grammar; they offer a unique window into the cognitive architecture of language and expose the current limitations of artificial systems that seek to replicate them. This project proposes an interd isciplinary study of linguistic errors produced by native Spanish speakers, with the aim of analyzing how current large language models (LLM) interpret, reproduce, or correct them. The research integrates three core perspectives: theoretical linguistics, to classify and understand the nature of the errors; neurolinguistics, to contextualize them within real - time language processing in the brain; and natural language processing (NLP), to evaluate their interpretation against linguistic errors. A purpose - built corpus of authentic errors of native Spanish (+500) will serve as the foundation for empirical analysis. These errors will be tested against AI models such as GPT or Gemini to assess their interpretative accuracy and their ability to generalize patterns of human linguistic behavior. The project contributes not only to the understanding of Spanish as a native language but also to the development of NLP systems that are more cognitively informed and capable of engaging with the imperfect, variable, and often ambiguous nature of real hum an language. In recent years, the development of large language models (LLMs) such as GPT - 4 and Gemini has brought a revolution in the field of natural language processing (NLP). These models, based on transformer architectures ( Vaswani et al., 2017), have demonstrated unprecedented abilities to generate coherent text, perform automatic translation, and produce complex summaries. Their impressive performance has transformed many applications, from chatbots and virtual assistants to automated content creation and languag e learning tools. However, despite these technological advances, LLMs still face significant challenges rooted in the inherently complex, ambiguous, and variable nature of real human language ( Bender et al., 2021). Particularly, irregularities, ambiguities, and errors commonly found in informal and spontaneous contexts, such as everyday conversations or social media interactions, constitute a major obstacle for the optimal functioning of these systems. Human language is not a rigid or perfectly normative system; rather, it is a dynamic phenomenon that reflects complex cognitive processes and is characterized by variations and errors in production and comprehension ( Levelt, 1989). Linguistic errors produced even by native speakers should not be dismissed as mere random deviations but regarded as systematic manifestations that can provide valuable insight into the internal functioning of the linguistic system and its neurological foundations ( Fromkin, 2013) .

Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability across different domains and resource settings. DINO-MX is a modular and extensible training framework that combines the core principles of DINO, DINOv2 and DINOv3 within a unified configuration-driven system. It supports a variety of transformer-based architectures and is fully compatible with the Hugging Face ecosystem. The framework includes multiple training strategies such as low-rank adaptation (LoRA), layer freezing, and knowledge distillation, along with support for distributed training through both Distributed Data Parallel (DDP) and Fully Sharded Data Parallel (FSDP). DINO-MX is designed to work with both natural and specialized data types, including single- and multi-channel images. Experimental results on diverse datasets show that DINO-MX achieves competitive performance while significantly reducing computational costs. Additionally, it offers interpretability tools and a label-guided data augmentation method that improves attention-based localization without the need for extra detection or segmentation heads. DINO-MX provides a reproducible and scalable foundation for developing, adapting, and benchmarking self-supervised vision models across a range of research and real-world applications.

Large language models (LLMs) universally suffer from knowledge staleness and lack of interpretability due to their implicit knowledge storage paradigm, where information is distributed across network parameters in an entangled, non-addressable manner. This fundamental limitation prevents targeted knowledge updates, verification of stored information, and understanding of model reasoning processes. We propose ExplicitLM, a novel architecture that fundamentally reimagines knowledge storage in language models through an explicit, interpretable memory bank system. Our key innovation introduces a million-scale external memory bank where each entry stores human-readable knowledge as token sequences, enabling direct inspection and modification of the model's knowledge base. To efficiently access this massive repository, we design a differentiable two-stage retrieval mechanism that enables end-to-end training while maintaining discrete knowledge selection, combining efficient coarse-grained filtering with product key decomposition (reducing computational complexity from O(N |I|) to O( N |I|)) and fine-grained similarity matching through Gumbel-Softmax. Drawing inspiration from dual-system cognitive theory, we partition knowledge into frozen explicit facts (20%) and learnable implicit patterns (80%), maintained through an Exponential Moving Average update strategy that ensures training stability.

Vision-Language-Action models (VLAs) are emerging as powerful tools for learning generalizable visuomotor control policies. However, current VLAs are mostly trained on large-scale image-text-action data and remain limited in two key ways: (i) they struggle with pixel-level scene understanding, and (ii) they rely heavily on textual prompts, which reduces their flexibility in real-world settings. To address these challenges, we introduce PixelVLA, the first VLA model designed to support both pixel-level reasoning and multimodal prompting with text and visual inputs. Our approach is built on a new visuomotor instruction tuning framework that integrates a multiscale pixel-aware encoder with a visual prompting encoder. To train PixelVLA effectively, we further propose a two-stage automated annotation pipeline that generates Pixel-160K, a large-scale dataset with pixel-level annotations derived from existing robot data. Experiments on three standard VLA benchmarks and two VLA model variants show that PixelVLA improves manipulation success rates by 10.1%-17.8% over OpenVLA, while requiring only 1.5% of its pretraining cost. These results demonstrate that PixelVLA can be integrated into existing VLAs to enable more accurate, efficient, and versatile robot control in complex environments. The dataset and code will be released as open source.

Controllable Dialogue Generation (CDG) enables chatbots to generate responses with desired attributes, and weighted decoding methods have achieved significant success in the CDG task. However, using a fixed constant value to manage the bias of attribute probabilities makes it challenging to find an ideal control strength that satisfies both controllability and fluency. To address this issue, we propose ECO decoding (Entropy-based COntrol), which dynamically adjusts the control strength at each generation step according to the model's entropy in both the language model and attribute classifier probability distributions. Experiments on the DailyDialog and MultiWOZ datasets demonstrate that ECO decoding consistently improves controllability while maintaining fluency and grammaticality, outperforming prior decoding methods across various models and settings. Furthermore, ECO decoding alleviates probability interpolation issues in multi-attribute generation and consequently demonstrates strong performance in both single and multi-attribute scenarios.

Math anxiety poses significant challenges for university psychology students, affecting their career choices and overall well-being. This study employs a framework based on behavioural forma mentis networks (i.e. cognitive models that map how individuals structure their associative knowledge and emotional perceptions of concepts) to explore individual and group differences in the perception and association of concepts related to math and anxiety. We conducted 4 experiments involving psychology undergraduates from 2 samples (n1 = 70, n2 = 57) compared against GPT-simulated students (GPT-3.5: n2 = 300; GPT-4o: n4 = 300). Experiments 1, 2, and 3 employ individual-level network features to predict psychometric scores for math anxiety and its facets (observational, social and evaluational) from the Math Anxiety Scale. Experiment 4 focuses on group-level perceptions extracted from human students, GPT-3.5 and GPT-4o's networks. Results indicate that, in students, positive valence ratings and higher network degree for "anxiety", together with negative ratings for "math", can predict higher total and evaluative math anxiety. In contrast, these models do not work on GPT-based data because of differences in simulated networks and psychometric scores compared to humans. These results were also reconciled with differences found in the ways that high/low subgroups of simulated and real students framed semantically and emotionally STEM concepts. High math-anxiety students collectively framed "anxiety" in an emotionally polarising way, absent in the negative perception of low math-anxiety students. "Science" was rated positively, but contrasted against the negative perception of "math". These findings underscore the importance of understanding concept perception and associations in managing students' math anxiety.