Background/Objectives: While artificial intelligence (AI) is rapidly transforming education, its specific effectiveness for students with learning disabilities (LD) requires rigorous evaluation. This systematic review aims to assess the efficacy of AI-based educational interventions for students with LD, with a specific focus on the methodological quality and risk of bias of the available evidence. Methods: A systematic search was conducted across seven major databases (Google Scholar, ScienceDirect, APA PsycInfo, ERIC, Scopus, PubMed) for experimental studies published between 2022 and 2025. This review followed PRISMA guidelines, using the PICOS framework for inclusion criteria. A formal risk of bias assessment was performed using the ROBINS-I and JBI critical appraisal tools. Results: Eleven studies (representing 10 independent experiments), encompassing 3033 participants, met the inclusion criteria. The most studied disabilities were dyslexia (six studies) and other specific learning disorders (three studies). Personalized/adaptive learning systems and game-based learning were the most common AI interventions. All 11 studies reported positive outcomes. However, the risk of bias assessment revealed significant methodological limitations: no studies were rated as having a low risk of bias, with most presenting a moderate (70%) to high/serious (30%) risk. Despite these limitations, quantitative results from the stronger studies showed large effect sizes, such as in arithmetic fluency (d = 1.63) and reading comprehension (d = −1.66). Conclusions: AI-based interventions demonstrate significant potential for supporting students with learning disabilities, with unanimously positive reported outcomes. However, this conclusion must be tempered by the considerable risk of bias and methodological weaknesses prevalent in the current literature. The limited and potentially biased evidence base warrants cautious interpretation. Future research must prioritize high-quality randomized controlled trials (RCTs) and longitudinal assessments to establish a definitive evidence base and investigate long-term effects, including the risk of cognitive offloading.

Until the first decade of the current millennium, the literature on metaphor comprehension highlighted typical difficulties in children with high-functioning Autism Spectrum Disorder (ASD). More recently, some scholars have devised special programs for enhancing the capability of understanding metaphors in these children. This article presents a case study based on a treatment aiming at enhancing novel metaphor comprehension in a high-functioning child with ASD. M.M., a pseudoacronym for an 8;10 year-old boy, diagnosed with high-functioning ASD, was first assessed with a metaphor comprehension test. This testing (at time T0) highlighted a rigid refusal of metaphors and a marked tendency toward literal interpretation. A baseline treatment (8 sessions of 45-60 minutes each, twice a week) was implemented, based on a series of recognition, denomination and emotion comprehension activities. MM’s metaphor comprehension was assessed a second time (T1), followed by the experimental treatment (same duration and frequency as the first one), specifically focused on metaphor comprehension. Finally, a third assessment of metaphor comprehension took place (T2), followed by a last assessment four months later (follow-up, T3).The comparison between the performances at the metaphor comprehension test across the four assessments, from T0 to T3, showed that the baseline treatment produced no effect at all, whereas a significant improvement appeared at T2, just after the experimental treatment, later confirmed at the follow up. Both quantitative and qualitative results showed an evident improvement in the way M.M. handled the semantic issues posed by the metaphors of the test, in line with the strategies he was taught during the treatment

Recent research into difficulties in figurative language in children with ASD highlighted that it is possible to devise training interventions to overcome these difficulties by teaching specific strategies. This study describes how children with ASD can improve their capability to explain metaphors with a treatment. Two types of metaphors, in the “X is Y” form, were addressed: sensory and physico-psychological. To face the difficulties posed by these metaphors, the adult taught two strategies: inserting the connective “is like” between “X” and “Y”, which transforms the metaphor into a simile; comparing “X” and “Y” by means of thinking maps. Two tests of metaphor comprehension were used, one based on sensory and the other on physico-psychological metaphors. Sixteen 10 year-old children participated into the study, including an experimental group formed by 8 children with ASD (n = 4) which had received the treatment, and a control group (n = 4) which had not, and 8 typically-developing (TD) children. At the post-test, the experimental group significantly outperformed the controls in explaining both types of metaphors, but only in the sensory metaphors did their performances reach TD children’s levels. These results illuminate how clinical treatment can positively influence the developmental trajectories of metaphor comprehension.

It is considered to be particularly interesting to enrich the scientific overview investigating the comorbidities of specific learning disorders (SLDs) in young adults. Therefore, this study aims to investigate the psychosocial and relational profiles associated with the presence of learning difficulties in a population of university students. The hypothesis is that young adults with SLDs have lower psychological and socio-relational functioning than their typical-development peers. We further hypothesized that the socio-relational difficulties of students with SLDs could be explained not only by referring to the presence of a learning disorder, but also by considering some variables that may follow the experience of students with SLDs. The results highlighted that students with SLDs, compared to their typical-development peers, have low self-efficacy, high academic anxiety scores, emotional problems, and issues with peers. We finally suggest considering these aspects as early as the diagnostic process to facilitate an effective treatment plan for learning disorders to prevent, in terms of developmental trajectory, the manifestation of these aspects in adulthood.

This article presents case studies on metaphor comprehension in two boys with high-functioning autistic spectrum disorder, aged 9;1 (9 years, 1 month) and 8;11. The participants were assessed twice, before and after an intervention program aimed at improving their social skills. The focus of the article is on the specific patterns exhibited by each child in a test of metaphor comprehension that elicits verbal explanation of metaphors, and is targeted at 4–6-year-old typically developing children. The two children had age-appropriate cognitive and verbal abilities, as measured by WISC-III and Peabody Picture Vocabulary Test. At the first assessment, performance on both children was within the average range of typically developing 5-year-old children, but they differed in their patterns of response. At the second time of assessment both the children’s performance had improved, but each in a different manner. The discussion reconsiders the qualitative aspects emerging from the assessments performed at the two time points of the study, raises theoretical issues about metaphor comprehension, and points to possible implications for diagnosis and intervention.

This study analyses the case of a gifted child (9;6 year) with autism spectrum disorder (ASD) who had a particularly high verbal IQ (146) and a specific cognitive, linguistic, and metalinguistic profile. A description of some salient behavioral characteristics of the child is provided. A metalinguistic ability test assessing metagrammatical, metasemantic, and metaphonological abilities and a metaphor comprehension test were administered. Both tests place high value on justifications of responses, which permits investigators to grasp different levels of metalinguistic awareness. The child gave poor metalinguistic responses in subtests assessing metasemantic abilities, contrary to subtests assessing metagrammatical and metaphonological abilities. These discrepant results are interpreted in terms of this child’s specific difficulty with ‘open’ linguistic systems, such as semantics, in spite of his high ‘closed’ language capabilities. The discussion highlights the importance of assessing the meta-level of the verbal competencies of gifted children with ASD.