Large Language Models (LLMs) are becoming increasingly integrated into our lives. Hence, it is important to understand the biases present in their outputs in order to avoid perpetuating harmful stereotypes, which originate in our own flawed ways of thinking. This challenge requires developing new benchmarks and methods for quantifying affective and semantic bias, keeping in mind that LLMs act as psycho-social mirrors that reflect the views and tendencies that are prevalent in society. One such tendency that has harmful negative effects is the global phenomenon of anxiety toward math and STEM subjects. In this study, we introduce a novel application of network science and cognitive psychology to understand biases towards math and STEM fields in LLMs from ChatGPT, such as GPT-3, GPT-3.5, and GPT-4. Specifically, we use behavioral forma mentis networks (BFMNs) to understand how these LLMs frame math and STEM disciplines in relation to other concepts. We use data obtained by probing the three LLMs in a language generation task that has previously been applied to humans. Our findings indicate that LLMs have negative perceptions of math and STEM fields, associating math with negative concepts in 6 cases out of 10. We observe significant differences across OpenAI’s models: newer versions (i.e., GPT-4) produce 5× semantically richer, more emotionally polarized perceptions with fewer negative associations compared to older versions and $N=159$ high-school students. These findings suggest that advances in the architecture of LLMs may lead to increasingly less biased models that could even perhaps someday aid in reducing harmful stereotypes in society rather than perpetuating them.

The computation of the fundamental magnetic and electric field coupling terms for the full-wave partial element equivalent circuit method is time consuming for large problems. Extensive numerical integration is required for the computation of four to six fold integration of the partial element coefficients. In this paper, we present new full-wave analytical formulas for their computation, which are based on several different Taylor series expansion approaches for the case of rectangular elementary volumes and surfaces.

To evaluate the validity and reliability of the amyotrophic lateral sclerosis assessment questionnaire (ALSAQ) in an Italian cohort of ALS patients and to further characterize the relationship between motor impairment and quality of life (QoL) in ALS. Seventy-six patients completed the Italian version of ALSAQ-40 and ALSAQ-5. To verify test-retest reliability, 30 patients were revaluated after 3 months. The medical outcome study short form 36 (MOS SF-36) questionnaire and revised ALS functional rating scale (ALSFR-R) scale were used to assess Italian ALSAQ-40 construct validity. The limb muscles' Medical Research Council (MRC) score and forced vital capacity (FVC) were used to measure the degree of motor impairment. The Italian ALSAQ-40 showed a very good internal consistency (all subscales Cronbach's alpha>0.86) and a good construct validity as shown by the patterns of correlation between the subscales and SF-36 (resp. ALSFRS-R) scores. ALSAQ-5 showed a positive correlation with the corresponding ALS patient total score and subscale scores of the ALSAQ-40 (Spearman's correlation coefficient>0.73). The emotional functioning subscale did not correlate with any motor impairment measures. Italian ALSAQ-40 and ALSAQ-5 psychometric properties are reliable and similar to those showed by the original English version. We observed emotional aspects to be distinct from physical involvement.

In this paper, we propose a novel parameterized model order reduction technique for circuits described by the delayed partial element equivalent circuit method. The moment vectors associated with frequency are excluded while forming the moments’ subspace. This leads to obtaining very compact parameterized reduced order models. An implicit multiparameter moment matching algorithm is used for the moments related to the design parameters. Numerical results validate the accuracy and efficiency of the proposed technique in both frequency- and time-domain. The time-domain response of the reduced order models is obtained using the numerical inversion of Laplace transform, which avoids stability issues as well as the computationally expensive repeated interpolation steps associated with conventional time-stepping integration method for delayed differential equations.