Testuen analisia

Optimal strategies to perform multilingual analysis of social content for a novel dataset in the tourism domain

Gehiago irakurri Optimal strategies to perform multilingual analysis of social content for a novel dataset in the tourism domain -ri buruz

BasqueParl: descifrar la huella retórica en el Parlamento Vasco con el procesamiento del lenguaje natural.

Gehiago irakurri BasqueParl: descifrar la huella retórica en el Parlamento Vasco con el procesamiento del lenguaje natural. -ri buruz

Benchmarking Critical Questions Generation: A Challenging Reasoning Task for Large Language Models

The task of Critical Questions Generation (CQs-Gen) aims to foster critical thinking by enabling systems to generate questions that expose underlying assumptions and challenge the validity of argumentative reasoning structures. Despite growing interest in this area, progress has been hindered by the lack of suitable datasets and automatic evaluation standards. This paper presents a comprehensive approach to support the development and benchmarking of systems for this task. We construct the first large-scale dataset including ~5K manually annotated questions.

Gehiago irakurri Benchmarking Critical Questions Generation: A Challenging Reasoning Task for Large Language Models -ri buruz

CRITICS - Critical Science Without Borders: LLMs for Translation of Scientific Knowledge in Multilingual Contexts

"Muga Gabeko Zientzia Kritikoa" CRITICS proiektuak ezagutza zientifikorako sarbidea demokratizatzea du helburu, eduki zientifikoaren itzulpen automatikorako Hizkuntza-Eredu Handi espezializatuak garatuz tokiko hizkuntzetan. Ekimenak hiru berrikuntza nagusi konbinatzen ditu: dokumentu zientifikoetarako IA sistema aurreratuak, tokiko testuinguruetara edukia egokitzen duten IAk sortutako Irakaskuntza-Ikaskuntza Sekuentziak, eta ikasleen ama hizkuntzetan pentsamendu kritikoa ebaluatzeko ebaluazio-tresna automatizatuak.

Gehiago irakurriCRITICS - Critical Science Without Borders: LLMs for Translation of Scientific Knowledge in Multilingual Contexts -ri buruz

DeepThought: Reasoning and Alignment of Large Language Models for Multilingual and Low Resource Scenarios

DeepThought-ek eskala handiko hurbilketa bat aurkezten du hizkuntza gutxituetarako Hizkuntza Eredu Handiak egokitzeko, prestakuntza eta lerrokadura estrategia berritzaile baten bidez. Proiektuak enpirikoki balioztatutako metodologiak garatuko ditu Llama-3+ eta Qwen+ bezalako kode irekiko ereduak euskara eta gaztelaniara zabaltzeko, lehendik dauden LLMen eta Hizkuntza Arrazonamendu Ereduen datu-multzo sintetikoak eta arrazonamendu-berbalizazioak aprobetxatuz.

Gehiago irakurriDeepThought: Reasoning and Alignment of Large Language Models for Multilingual and Low Resource Scenarios -ri buruz

Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data

Gehiago irakurriLemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data -ri buruz

Humanizing AI with language technology (HumanAIze)

The "Humanizing AI with Language Technology (HumanAIze)" project seeks to enhance Large Language Models (LLMs) to make them more human, reliable, and ethical by addressing weaknesses such as bias, cultural understanding, and reliability. Six research centers bring their expertise in areas such as multilingualism, anonymization, verification, and evaluation. A key approach is "reliable by design," implementing ethical and legal principles, data governance, human feedback, and sustainability.

Gehiago irakurriHumanizing AI with language technology (HumanAIze) -ri buruz

EFICIENCIA DE MODELOS LLM PARA INDUSTRIAS ESTRATÉGICAS (EMIE) (2025.0736)

HAZITEK ESTRATEGIKOA. EMIE. RVCTI AZPIKONTRATAZIOA LLMak industrian duten erabilera ebaluatzeko proiektua. RVCTI azpikontratazioa HAZITEK estrategiko batean.

Gehiago irakurriEFICIENCIA DE MODELOS LLM PARA INDUSTRIAS ESTRATÉGICAS (EMIE) (2025.0736) -ri buruz

Metaphor and Large Language Models: When Surface Features Matter More than Deep Understanding

Gehiago irakurriMetaphor and Large Language Models: When Surface Features Matter More than Deep Understanding -ri buruz

Dynamic Knowledge Integration for Evidence-Driven Counter-Argument Generation with Large Language Models

Gehiago irakurriDynamic Knowledge Integration for Evidence-Driven Counter-Argument Generation with Large Language Models -ri buruz

Hizkuntzak

Nor gara?

Zer egiten dugu?

Beste batzuk