108495 research outputs found
Sort by
Arendamine ja juurutamine uue rolli andmetele juurdepääsu piiramiseks mitme kasutajaga rakenduses SettleInEstonia
No full texthttps://www.ester.ee/record=b574006
Investigating Further Fine-tuning Wav2vec2.0 in Low Resource Settings for Enhancing Children Speech Recognition and Word-level Reading Diagnosis
No full textTowards Multilingual LLM Evaluation for Baltic and Nordic languages: A study on Lithuanian History
No full textIn this work, we evaluated Lithuanian and general history knowledge of multilingual Large Language Models (LLMs) on a multiple-choice question-answering task. The models were tested on a dataset of Lithuanian national and general history questions translated into Baltic, Nordic, and other languages (English, Ukrainian, Arabic) to assess the knowledge sharing from culturally and historically connected groups. We evaluated GPT-4o, LLaMa3.1 8b and 70b, QWEN2.5 7b and 72b, Mistral Nemo 12b, LLaMa3 8b, Mistral 7b, LLaMa3.2 3b, and Nordic fine-tuned models (GPT-SW3 and LLaMa3 8b). Our results show that GPT-4o consistently outperformed all other models across language groups, with slightly better results for Baltic and Nordic languages. Larger open-source models like QWEN2.5 72b and LLaMa3.1 70b performed well but showed weaker alignment with Baltic languages. Smaller models (Mistral Nemo 12b, LLaMa3.2 3b, QWEN 7B, LLaMa3.1 8B, and LLaMa3 8b) demonstrated gaps with Lithuanian national history related questions (LT-related) alignment with Baltic languages while performing better on Nordic and other languages. The Nordic fine-tuned models did not surpass multilingual models, indicating that shared cultural or historical context alone does not guarantee better performance
Evaluating LLM Judgment on Latvian and Lithuanian Short Answer Matching
No full textIn this work, we address the challenge of evaluating large language models (LLMs) on the short answer matching task for Latvian and Lithuanian languages. We introduce novel datasets consisting of 502 Latvian and 690 Lithuanian question-answer pairs. For each question-answer pair, we generated matched and non-matched answers using a set of alteration rules specifically designed to introduce small but meaningful changes in the text. These generated answers serve as test cases to assess the ability of LLMs to detect subtle differences in matching of the original answers. A subset of the datasets was manually verified for quality and accuracy. Our results show that while larger LLMs, such as QWEN2.5 72b and LLaMa3.1 70b, demonstrate near-perfect performance in distinguishing matched and non-matched answers, smaller models show more variance. For instance, LLaMa3.1 8b and EuroLLM 9b benefited from few-shot examples, while Mistral Nemo 12b underperformed on detection of subtle text alteration, particularly in Lithuanian, even with additional examples. QWEN2.5 7b and Mistral 7b were able to obtain a strong and comparable performance to the larger 70b models in zero and few shot experiments.
Moreover, the performance of Mistral 7b was weaker in few shot experiments. The code and the dataset are available on our GitHub
Teachers’ attitudes toward and intervention in child-to-child conflict
No full textKäesoleva uuringu eesmärk oli välja selgitada, kuidas õpetajate suhtumine lastevahelisse konflikti on seotud õpetaja sekkumisega lastevahelisse konflikti. Valimisse kuulus 259 Eesti õpetajat, kes vastasid küsimustele lastevaheliste konfliktide ning õpetaja konfliktis käitumise kohta. Uuringu tulemused näitasid nõrka negatiivset seost konflikti positiivselt suhtumise ja direktiivse sekkumise vahel. Seost positiivse suhtumise ning vahendava sekkumise vahel ei leitud. Samuti leiti nõrk positiivne korrelatsioon konflikti suhtumise ning konflikti mitte sekkumise vahel. Tulemused viitavad sellele, et mida positiivsemalt suhtuvad õpetajad lastevahelisse konflikti, seda vähem kasutavad nad lastevahelisse konflikti sekkumisel direktiivset käitumist või ei sekku konflikti üldse
Beliefs about masculine personality traits and their association to mental health and stigma
Get PDFErinevad uskumused ja hinnangud mõjutavad seda, kuidas tajume maailma. Uurimistöö eesmärgiks oli uurida, mida peetakse isiksuseküsimustiku 100NP (One Hundred Nuances of Personality) 198 väite põhjal mehelikuks ning, kas nende uskumuste vahel esineb seos selle inimese vaimse tervise ning personaalse ja tajutud stigmaga. Uuringus kasutati 114 osaleja andmeid, kellest 85,1% olid naised (n = 97) ja 14,0% mehed (n = 16), valimi keskmine vanus oli 27,9 eluaastat (SD = 11,43). Seoste uurimiseks kasutati antud inimeste hinnangute kooskõla stereotüüpse profiiliga ning vaimset tervist ja stigmat hindavaid mõõdikuid. Lisaks leiti seosed kümne kõige kõrgema ja madalama skoori saanud väidete ning vaimset tervist ja stigmat hindavate mõõdikute vahel. Kõige mehelikemate ja mittemehelikemate hinnangute ning vaimse tervise probleemide ja stigma vahel esines statistiliselt olulisi seoseid. Uuring aitas paremini mõista, millised uskumused mehelikkuse kohta endiselt eksisteerivad ning, kuidas need on seotud vaimse tervisega
