Search Results (309)

Some large language models (LLMs) are open source and are therefore fully open for scientific study. However, many LLMs are proprietary, and their internals are hidden, which hinders the ability of the research community to study their behavior under controlled conditions. For instance, the token input embedding specifies an internal vector representation of each token used by the model. If the token input embedding is hidden, latent semantic information about the set of tokens is unavailable to researchers. This article presents a general and flexible method for prompting an LLM to reveal its token input embedding, even if this information is not published with the model. Moreover, this article provides strong theoretical justification—a mathematical proof for generic LLMs—for why this method should be expected to work. If the LLM can be prompted systematically and certain benign conditions about the quantity of data collected from the responses are met, the topology of the token embedding is recovered. With this method in hand, we demonstrate its effectiveness by recovering the token subspace of the Llemma-7BLLM. We demonstrate the flexibility of this method by performing the recovery at three different times, each using the same algorithm applied to different information collected from the responses. While the prompting can be a performance bottleneck depending on the size and complexity of the LLM, the recovery runs within a few hours on a typical workstation. The results of this paper apply not only to LLMs but also to general nonlinear autoregressive processes. Full article

Background/Objectives: This study examines the impact of long-term institutionalization on the linguistic and communicative abilities of people diagnosed with schizophrenia, focusing on the influence of educational background. Schizophrenia is characterized by cognitive and social deficits, including disruptions to language use and communicative engagement. Prolonged institutionalization can exacerbate these impairments by depriving individuals of essential social interactions and cognitive stimulation. Methods: A case series approach was employed with 18 participants, and validated assessment tools such as the Montreal Evaluation of Communication and the Boston Diagnostic Aphasia Test were used to measure communicative performance. Results: Participants with higher educational attainment (nine or more years of schooling) who had been institutionalized for ten years or more exhibited significantly better performance than their less-educated counterparts across various communication domains, including comprehension of linguistic prosody, lexical fluency, and auditory comprehension. This implies that completing a higher degree may mitigate the cognitive decline impact of prolonged stays in an institution. However, the study design does not allow us to ascertain whether education functions as a mitigating factor. Conclusions: The results highlight the importance of incorporating educational considerations into therapeutic strategies for individuals with schizophrenia, especially those experiencing long-term institutionalization. Providing enhanced educational opportunities within institutional settings could mitigate the adverse effects of prolonged confinement and foster improved communication and social skills. These findings are consistent with research on cognitive reserve, which suggests that education fosters adaptive strategies and the utilization of alternative neural pathways. This enables individuals to maintain communication skills despite the cognitive impairment associated with schizophrenia. Full article

This study investigates the utilisation of AI tools, including Grammarly Free, QuillBot Free, Canva Free Individual, and others, to enhance learning outcomes for 180 s-year telecommunications engineering students at Universidad Politécnica de Madrid. This research incorporates teaching methods like problem-based learning, experiential learning, task-based learning, and content–language integrated learning, with English as the medium of instruction. These tools were strategically used to enhance language skills, foster computational thinking, and promote critical problem-solving. A control group comprising 120 students who did not receive AI support was included in the study for comparative analysis. The control group’s role was essential in evaluating the impact of AI tools on learning outcomes by providing a baseline for comparison. The results indicated that the pilot group, utilising AI tools, demonstrated superior performance compared to the control group in listening comprehension (98.79% vs. 90.22%) and conceptual understanding (95.82% vs. 84.23%). These findings underscore the significance of these skills in enhancing communication and problem-solving abilities within the field of engineering. The assessment of the pilot course’s forum revealed a progression from initially error-prone and brief responses to refined, evidence-based reflections in participants. This evolution in responses significantly contributed to the high success rate of 87% in conducting complex contextual analyses by pilot course participants. Subsequent to these results, a project for educational innovation aims to implement the AI-PBL-CLIL model at Universidad Politécnica de Madrid from 2025 to 2026. Future research should look into adaptive AI systems for personalised learning and study the long-term effects of AI integration in higher education. Furthermore, collaborating with industry partners can significantly enhance the practical application of AI-based methods in engineering education. These strategies facilitate benchmarking against international standards, provide structured support for skill development, and ensure the sustained retention of professional competencies, ultimately elevating the international recognition of Spain’s engineering education. Full article

Background/Objectives: Feeding and swallowing difficulties are common in young children with cerebral palsy (CP), yet no validated tool has been available in Korea for those under 3 years. The Mini-Eating and Drinking Ability Classification System (Mini-EDACS) was designed for children aged 18–36 months. This study aimed to translate the Mini-EDACS into Korean and evaluate its reliability and validity. Methods: Translation followed international guidelines, including forward–backward translation and Delphi consensus with experts in pediatric dysphagia. Forty-eight children with CP (mean age 27.1 ± 5.0 months) were assessed. Caregivers and speech–language pathologists (SLPs) independently rated Mini-EDACS and assistance levels. Inter-rater reliability was examined using Cohen’s κ. Construct validity was tested by Spearman’s correlations with the Gross Motor Function Classification System (GMFCS), Mini-MACS, the Communication Function Classification System (CFCS), the Visual Function Classification System (VFCS), and the Functional Oral Intake Scale for Children (FOIS-C). Results: Agreement between caregivers and SLPs was excellent (κ = 0.90; weighted κ = 0.98). Assistance-level ratings also showed almost perfect concordance (κ = 0.97). Mini-EDACS correlated strongly with FOIS-C (ρ = −0.86, p < 0.001) and with assistance levels (ρ = 0.81, p < 0.001). Moderate-to-strong positive correlations were observed with GMFCS (ρ = 0.56), Mini-MACS (ρ = 0.64), CFCS (ρ = 0.61), and VFCS (ρ = 0.61), supporting construct validity. Conclusions: The Korean Mini-EDACS is a reliable and valid tool for classifying eating and drinking abilities in children with CP under 3 years. It enables standardized communication between caregivers and clinicians, complements existing functional classification systems, and may facilitate earlier identification and intervention for feeding difficulties. Full article

This pilot study examined how sociodemographic factors (age, education, internet usage) influence patients’ comprehension of written healthcare communications, and their understanding of patient rights as articulated in appointment letters. A cross-sectional study was conducted among in-clinic patients at three Danish hospitals. Participants completed a self-administered questionnaire, assessing health literacy through four domains: assessing, understanding, appraising, and applying information from appointment letters. The questionnaire included sociodemographic data, Internet usage, IT competencies, and self-assessed health. Overall, 364 patients participated, with the majority being female and aged between 35 and 74 years. The mean scores for the domains of understanding and applying information were higher compared to assessing and appraising. Multiple linear regression analysis revealed that higher education levels positively correlated with the ability to appraise legal information, while frequent internet usage also enhanced appraisal skills. Findings highlight a concerning gap in patients’ ability to understand and appraise their patient rights within written healthcare communications. While patients demonstrate reasonable skills in understanding basic information, critical legal aspects remain challenging. Enhancing education and digital literacy may improve comprehension, emphasizing the need for simplified language and alternative formats in appointment letters. Further research is warranted to optimize communication strategies for patient rights. Full article

Recovery from aphasia is a complex process involving restoring language ability to a level comparable to an individual’s pre-aphasia state. This recovery extends beyond linguistic functions such as improved quality of life and functional communication. Understanding language recovery in PWAs is a key area in aphasia research. Thus, the current study aimed to understand the pattern of language recovery in the acute and sub-acute stages of persons with aphasia (PWAs). A total of 11 PWAs aged between 40 and 80 were recruited. The study was conducted in two phases. In the acute stage (within one week post-stroke), participants were assessed using the Western Aphasia Battery-Kannada (WAB-K). In the sub-acute stage (between seven and fifteen days post-stroke), a similar test battery was repeated. The findings of the study showed auditory verbal comprehension scores were pronounced in the acute and sub-acute stages of recovery. Further, language quotient (LQ) scores were higher in the sub-acute stage compared to the acute stage, though these differences failed to evince statistical differences. Correlation analysis revealed strong positive correlations between LQ and spontaneous speech, repetition, and naming, with moderate correlations for auditory verbal comprehension. The study’s findings highlight the importance of targeted therapeutic interventions for PWAs, emphasizing an early focus on auditory verbal comprehension to enhance overall language recovery. Full article

Background: Speech and Language Impairment (SLI) significantly affects children’s communication skills, limiting their social and academic development. Case Information: This single-case study evaluates the effects of a personalized intervention in a 9-year-old child diagnosed with SLI, integrating linguistic and cognitive strategies to remediate core deficits typically observed in children with SLI. Two main objectives were established: (1) to assess the child’s psycholinguistic competencies and cognitive processes and (2) to analyze the impact of the intervention on skills such as phonology, semantics, syntax, executive functions, and emotional well-being. The longitudinal and personalized design included pre- and post-intervention assessments conducted over two and a half years using tools such as the ITPA and Peabody Vocabulary Test. The intervention sessions were structured into linguistic and cognitive activities, with a frequency of two weekly language sessions and one cognitive functions session. Statistical analysis included ANOVA to evaluate significant changes. Conclusions: The results showed significant improvements in linguistic areas such as auditory comprehension (from 3–5 to 10 years) and verbal expression (from 5–10 to 9–6), as well as in cognitive aspects such as visuomotor sequential memory and visual comprehension, which exceeded the expected values for the child’s age. However, skills such as grammatical integration and auditory association did not show significant progress. This demonstrates that personalized and multidisciplinary interventions can considerably improve linguistic and cognitive abilities in children with SLI, although some areas require more specific approaches. The findings highlight implications for designing tailored intervention strategies, emphasizing the need for further research with larger samples and control groups to generalize the results. This case reaffirms the importance of comprehensive approaches in the treatment of SLI to maximize the academic and social development of affected children. Full article

Background: Aphasia, a common consequence of left-hemisphere stroke, significantly impairs communication and daily functioning. Various studies have explored language recovery but only few have focused on the predictors of recovery of functional communication in patients with stroke. Objective: To identify clinical and linguistic factors associated with functional communication outcomes in patients with post-stroke aphasia. Methods: We enrolled 61 patients with aphasia due to left-hemispheric stroke, admitted to post-acute neurorehabilitation centers. Patients underwent neuropsychological, functional, and language assessments at admission (T0) and discharge (T1). Language abilities were evaluated with the Brief Exam of Language—II (BEL-II), and functional communication was measured through caregiver-rated I-CETI scores. Depression, basic (ADL) and instrumental (IADL) activities of daily living were also assessed. Correlations and regression models were used to examine predictors of functional communication recovery (ΔCETI). Results: Significant improvements were observed in all language domains, functional independence, and mood symptoms from T0 to T1 (p < 0.003). Regression analysis showed that demographic and general clinical variables (e.g., age, etiology, dysphagia) were not significant predictors of ΔCETI. However, ADL score, comprehension skills (Token test and comprehension sub-score of BEL-II) were significantly associated with functional communication recovery (β = 0.51, β = 0.68 and β = 0.75, respectively; p < 0.05). Conclusions: Functional communication recovery in post-stroke aphasia is strongly associated with initial comprehension abilities and functional autonomy in basic life activities, rather than demographic or general clinical variables. These findings highlight the need for targeted interventions aimed at improving receptive language and the importance of including ecologically valid communication assessments in post-stroke rehabilitation protocols. Full article

Objectives: Individuals with Autism Spectrum Disorder (ASD) exhibit difficulties in the social use of language, regardless of age, cognitive abilities, and symptom severity. The left Broca’s area and adjacent cortex are crucial for socio-pragmatic language, particularly in retrieving and integrating context-dependent words. Neuroimaging studies in ASD have shown hypoactivation of the Broca’s area and an aberrant pattern of functional connectivity between language-related regions, suggesting their potential involvement in socio-communicative deficits. Given the potential of tDCS to modulate brain activity, its application targeting Broca’s areas in addition to psychological intervention may represent a promising approach for enhancing socio-communicative skills in ASD. Thus, this study aims to investigate the effect of concomitant anodal tDCS and cognitive behavioral-oriented training (CBT) on pragmatic and communicative skills in young adults with ASD. Methods: A sample of 10 ASD individuals (18–25 years) underwent treatment with both active and sham tDCS targeting the left Broca’s area during concomitant CBT. Each condition was delivered for five consecutive days, and the order of the conditions was blindly randomized. Results: Active tDCS significantly improved global communicative and pragmatic abilities compared to sham. A negative correlation was observed between communicative skills improvement and Intelligence Quotient (IQ); no significant association was found between IQ and ASD symptoms’ severity. Conclusions: Multisession tDCS targeting the left Broca’s area, combined with CBT, may enhance social language in terms of both production and comprehension of non-literal meanings, supporting Broca’s area as a central neural hub for social language. Full article

Biological swarms communicate through decentralized, adaptive behaviors shaped by local interactions, selective attention, and symbolic signaling. These principles of animal communication enable robust coordination without centralized control or persistent connectivity. This work presents a proof of concept that identifies, evaluates, and translates biological communication strategies into a generative visual language for unmanned aerial vehicle (UAV) swarm agents operating in radio-frequency (RF)-denied environments. Drawing from natural exemplars such as bee waggle dancing, white-tailed deer flagging, and peacock feather displays, we construct a configuration space that encodes visual messages through trajectories and LED patterns. A large language model (LLM), preconditioned using retrieval-augmented generation (RAG), serves as a generative translation layer that interprets perception data and produces symbolic UAV responses. Five test cases evaluate the system’s ability to preserve and adapt signal meaning through within-modality fidelity (maintaining symbolic structure in the same modality) and cross-modal translation (transferring meaning across motion and light). Covariance and eigenvalue-decomposition analysis demonstrate that this bio-agentic approach supports clear, expressive, and decentralized communication, with motion-based signaling achieving near-perfect clarity and expressiveness (0.992, 1.000), while LED-only and multi-signal cases showed partial success, maintaining high expressiveness (~1.000) but with much lower clarity (≤0.298). Full article

This study investigates how second language (L2) learners of Spanish identify the regional origin of native Spanish speakers and whether specific phonetic cues predict dialect identification accuracy across proficiency levels. Situated within a growing body of work on sociolinguistic competence, this research addresses the development of learners’ ability to use linguistic forms not only for communication but also for social interpretation. A dialect identification task was administered to 111 American English-speaking learners of Spanish and 19 native Spanish speakers. Participants heard sentence-length stimuli targeting regional phonetic features and selected the speaker’s country of origin. While L2 learners were able to identify regional dialects above chance, accuracy was low and significantly below that of native speakers. Higher-proficiency learners demonstrated improved identification, especially for speakers from Spain and Argentina, and relied more on salient phonetic cues (e.g., [θ], [ʃ]). No significant development was found for identification of Mexican or Puerto Rican varieties. Unlike native speakers, L2 learners did not show sensitivity to broader macrodialect groupings; instead, they frequently defaulted to high-exposure varieties (e.g., Spain, Mexico) regardless of the phonetic cues present. Findings suggest that sociophonetic perception in L2 Spanish develops gradually and unevenly, shaped by cue salience and exposure. Full article

Sign language recognition (SLR) plays a crucial role in bridging the communication gap between deaf individuals and the hearing population. However, achieving subject-independent SLR remains a significant challenge due to variations in signing styles, hand shapes, and movement patterns among users. Traditional Markov Chain-based models struggle with generalizing across different signers, often leading to reduced recognition accuracy and increased uncertainty. These limitations arise from the inability of conventional models to effectively capture diverse gesture dynamics while maintaining robustness to inter-user variability. To address these challenges, this study proposes an adaptive SLR framework that integrates Markov Chains with a Niching Genetic Algorithm (NGA). The NGA optimizes the transition probabilities and structural parameters of the Markov Chain model, enabling it to learn diverse signing patterns while avoiding premature convergence to suboptimal solutions. In the proposed SLR framework, GA is employed to determine the optimal transition probabilities for the Markov Chain components operating across multiple signing contexts. To enhance the diversity of the initial population and improve the model’s adaptability to signer variations, a niche model is integrated using a Context-Based Clearing (CBC) technique. This approach mitigates premature convergence by promoting genetic diversity, ensuring that the population maintains a wide range of potential solutions. By minimizing gene association within chromosomes, the CBC technique enhances the model’s ability to learn diverse gesture transitions and movement dynamics across different users. This optimization process enables the Markov Chain to better generalize subject-independent sign language recognition, leading to improved classification accuracy, robustness against signer variability, and reduced misclassification rates. Experimental evaluations demonstrate a significant improvement in recognition performance, reduced error rates, and enhanced generalization across unseen signers, validating the effectiveness of the proposed approach. Full article

Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disorder that progressively impairs motor and communication abilities. Globally, the prevalence of ALS was estimated at approximately 222,800 cases in 2015 and is projected to increase by nearly 70% to 376,700 cases by 2040, primarily driven by demographic shifts in aging populations, and the lifetime risk of developing ALS is 1 in 350–420. Despite international advancements in assistive technologies, a recent national survey in Saudi Arabia revealed that 100% of ALS care providers lack access to eye-tracking communication tools, and 92% reported communication aids as inconsistently available. While assistive technologies such as speech-generating devices and gaze-based control systems have made strides in recent decades, they primarily support English speakers, leaving Arabic-speaking ALS patients underserved. This paper presents SOUTY, a cost-effective, mobile-based application that empowers ALS patients to communicate using gaze-controlled interfaces combined with a text-to-speech (TTS) feature in Arabic language, which is one of the five most widely spoken languages in the world. SOUTY (i.e., “my voice”) utilizes a personalized, pre-recorded voice bank of the ALS patient and integrated eye-tracking technology to support the formation and vocalization of custom phrases in Arabic. This study describes the full development life cycle of SOUTY from conceptualization and requirements gathering to system architecture, implementation, evaluation, and refinement. Validation included expert interviews with Human–Computer Interaction (HCI) expertise and speech pathology specialty, as well as a public survey assessing awareness and technological readiness. The results support SOUTY as a culturally and linguistically relevant innovation that enhances autonomy and quality of life for Arabic-speaking ALS patients. This approach may serve as a replicable model for developing inclusive Augmentative and Alternative Communication (AAC) tools in other underrepresented languages. The system achieved 100% task completion during internal walkthroughs, with mean phrase selection times under 5 s and audio playback latency below 0.3 s. Full article

DIALOGUE (DIagnostic AI Learning through Objective Guided User Experience) is a generative artificial intelligence (GenAI)-based training program designed to enhance diagnostic communication skills in medical students. In this single-arm pre–post study, we evaluated whether DIALOGUE could improve students’ ability to disclose a type 2 diabetes mellitus (T2DM) diagnosis with clarity, structure, and empathy. Thirty clinical-phase students completed two pre-test virtual encounters with an AI-simulated patient (ChatGPT, GPT-4o), scored by blinded raters using an eight-domain rubric. Participants then engaged in ten asynchronous GenAI scenarios with automated natural-language feedback. Seven days later, they completed two post-test consultations with human standardized patients, again evaluated with the same rubric. Mean total performance increased by 36.7 points (95% CI: 31.4–42.1; p < 0.001), and the proportion of high-performing students rose from 0% to 70%. Gains were significant across all domains, most notably in opening the encounter, closure, and diabetes specific explanation. Multiple regression showed that lower baseline empathy (β = −0.41, p = 0.005) and higher digital self-efficacy (β = 0.35, p = 0.016) independently predicted greater improvement; gender had only a marginal effect. Cluster analysis revealed three learner profiles, with the highest-gain group characterized by low empathy and high digital self-efficacy. Inter-rater reliability was excellent (ICC ≈ 0.90). These findings provide empirical evidence that GenAI-mediated training can meaningfully enhance diagnostic communication and may serve as a scalable, individualized adjunct to conventional medical education. Full article

Background/Objectives: Accurate and accessible perioperative health information empowers patients and enhances recovery outcomes. Artificial intelligence tools, such as ChatGPT, have garnered attention for their potential in health communication. This study evaluates the accuracy and readability of responses generated by ChatGPT to questions commonly asked about breast cancer. Methods: Fifteen simulated patient queries about breast cancer surgery preparation and recovery were prepared. Responses generated by ChatGPT (4o version) were evaluated for accuracy by a pool of breast surgeons using a 4-point Likert scale. Readability was assessed with the Flesch–Kincaid Grade Level (FKGL). Descriptive statistics were used to summarize the findings. Results: Of the 15 responses evaluated, 11 were rated as “accurate and comprehensive”, while 4 out of 15 were deemed “correct but incomplete”. No responses were classified as “partially incorrect” or “completely incorrect”. The median FKGL score was 11.2, indicating a high school reading level. While most responses were technically accurate, the complexity of language exceeded the recommended readability levels for patient-directed materials. Conclusions: The model shows potential as a complementary resource for patient education in breast cancer surgery, but should not replace direct interaction with healthcare providers. Future research should focus on enhancing language models’ ability to generate accessible and patient-friendly content. Full article