Actualités & Insights

Restez à la pointe de la tech

Veille technologique, conseils d'experts et actualités sur l'IA, la cybersécurité, les réseaux et la transformation digitale.

674
Articles publiés
11915
Lectures cumulées
0
Auteurs
Tous 674 🔐 Cybersécurité 415 🤖 Intelligence Artificielle 253 💻 Tech & Transformation Digitale 6
Chargement…
🧠
Intelligence Artificielle

How Do Prompt Variations Affect Energy Consumption in On-Device LLMs?

arXiv:2609.01798v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed on mobile devices, making energy efficiency a key deployment constraint, yet the energy impact of prompt design remains underexplored. This paper aims to understand how two prompt properties, cognitive load and phrasing pattern, shape the energy behavior of on-device LLM…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization

arXiv:2609.01794v1 Announce Type: new Abstract: How do learners avoid overgeneralizations such as Tom laughed me without explicit negative evidence? Constructionists have posited two proposals that describe indirect negative evidence against overgeneralizations: preemption (which privileges exposure to near-synonymous construction---e.g., she made him laugh) vs. entrenchment…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

VakyArth: Evaluating Pragmatic Competence in LLMs across Indic Languages

arXiv:2609.01788v1 Announce Type: new Abstract: Real-world communication often requires pragmatic reasoning: interpreting meanings implied through context and cultural convention rather than stated literally. Existing pragmatic evaluation remains largely limited to English and high-resource languages, leaving Indic languages unexplored despite their linguistic and cultural…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

MemeCULT-1K: Benchmarking South Asian Cultural Context and Humor Understanding of Multimodal Models

arXiv:2609.01772v1 Announce Type: new Abstract: Meme understanding goes beyond recognizing visual content or literal text; it requires implicit cultural knowledge and pragmatic inference that most vision-language models still lack. We introduce MemeCULT-1K, a multilingual benchmark of 1,000 South Asian memes in Bengali, English, and Hindi, where each meme is paired with a…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition

arXiv:2609.01737v1 Announce Type: new Abstract: Mobile payment applications in Nepal are graphically mediated and largely inaccessible to visually impaired users. This paper presents SpeakPay, a voice-first digital wallet, and documents the central technical contribution: a controlled study of domain adaptation for low-resource financial speech recognition. We introduce…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

Learning Evidence Sufficiency Boundaries for Selective Answering in Grounded Multi-Hop QA

arXiv:2609.01687v1 Announce Type: new Abstract: Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult because partial evidence can make an unsupported answer appear plausible. We study selective answering through evidence sufficiency boundaries: for the same question, a model…

--
Équipe
1 min
Lire l'article