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.

676
Articles publiés
12404
Lectures cumulées
0
Auteurs
Tous 676 🔐 Cybersécurité 417 🤖 Intelligence Artificielle 253 💻 Tech & Transformation Digitale 6
Chargement…
🧠
Intelligence Artificielle

The Imperfective Paradox Is Not Necessarily in Large Language Models: A Benchmark Failure Before a Model Failure

arXiv:2608.25005v1 Announce Type: new Abstract: The imperfective paradox provides a useful test of compositional semantic analysis. Recent work constructs an NLI benchmark and reports that models frequently infer completed telic events from progressive descriptions, attributing this behavior to a Teleological Bias. It further argues that prompting interventions cause a…

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

Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal

arXiv:2608.24988v1 Announce Type: new Abstract: Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a way to encode alignment prior to release. However, models are routinely fine-tuned after deployment, and it is unknown whether embedded interventions survive this. We study the…

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

Unsupervised Post-Training of Foundation Models: A Survey

arXiv:2608.24982v1 Announce Type: new Abstract: Foundation-model post-training usually relies on human labels, preference data, stronger teachers, or executable verifiers. We study Unsupervised Post-Training (UPT): update-bearing adaptation on unlabeled inputs whose learning signal is derived from same-lineage model artifacts rather than an external oracle. We catalog 80…

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

The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline

arXiv:2608.24952v1 Announce Type: new Abstract: Systematic dialectal performance gaps in language models (LMs) are well documented, but the source of these disparities within the modern language modeling pipeline remains unclear. Our study traces this "dialect tax" across the natural language processing pipeline. Using parallel English dialect corpora that hold meaning fixed…

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

Semantic Variability of Replies Across LLMs: Implications for Designing Conversation-Based Assessment

arXiv:2608.24920v1 Announce Type: new Abstract: This study examines whether LLM-generated replies remain semantically consistent when the underlying LLM changes. Using messages from real collaborative conversations, we compared the semantic similarity of generated replies across LLMs under two conditions: with and without preceding chat history. Results show that model choice…

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

Detection != Reliable Control: Decodable Empathy Directions Yield at Most Partial Shifts in Automated Empathy Scores

arXiv:2608.24901v1 Announce Type: new Abstract: A decodable "empathy" direction is routinely read as a causal lever, conflating decodability, automated-metric control, and human-perceived change. We test this for two EPITOME-derived facets -- Recognition (cognitive) and Resonance (affective) -- in three instruction-tuned LLMs, scoring every intervention with two LLM judges…

--
Équipe
1 min
Lire l'article