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
12317
Lectures cumulées
0
Auteurs
Tous 676 🔐 Cybersécurité 417 🤖 Intelligence Artificielle 253 💻 Tech & Transformation Digitale 6
Chargement…
🧠
Intelligence Artificielle

Self- and Other-Labels Induce Bidirectional Bias in LLM Judges

arXiv:2608.18091v1 Announce Type: new Abstract: As LLM-as-a-judge systems become increasingly widespread, self-preference in LLMs -- the tendency to favor one's own outputs -- raises growing concerns about evaluation reliability. However, it has been studied predominantly on generated text, where stylistic features and response quality are inevitably conflated. As a result,…

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

Nine Emotion Centroids: A Label-Free Valence Axis That Transfers Across Four Modalities

arXiv:2608.18090v1 Announce Type: new Abstract: Inside a modern language model sits a single internal direction that tracks how positive or negative a sentence feels. We show how to find this valence axis (V-axis) from just 9 emotion category names plus 50 short narrative paragraphs per emotion -- about 1,500 fewer labels than the usual supervised approach -- and that the…

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

Latent Space Refusal Anchoring for Low-Resource African Languages: Mechanistic Safety Recovery Without Retraining

arXiv:2608.18089v1 Announce Type: new Abstract: Instruction-tuned models often refuse harmful requests in English but comply with the same requests in Yoruba, Igbo, Igala, and Hausa. This suggests that the refusal mechanism is present in the residual stream but fails to activate for low-resource inputs. Recovering it normally requires labelled target-language data and…

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

SuTRA : Structurally-Unified Tokenization with Root Awareness

arXiv:2608.18087v1 Announce Type: new Abstract: Existing subword tokenizers optimize statistical compression but ignore morphological structure, particularly the relationship between roots and affixes. This is harmful for morphologically rich Indic languages, where basic units are complex orthographic syllables (aksharas) rather than letters. Frequency-based methods…

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

Persona-Guided LLM Agents for Task-Oriented Dialogue

arXiv:2608.18085v1 Announce Type: new Abstract: Prior work has shown that large language models (LLMs) can express diverse personality traits in open-ended text generation. However, it remains unclear whether they can do so in a goal-directed dialogue without compromising task completion, and whether adapting to the user's personality improves the interaction quality. We…

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

Compiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem Proving

arXiv:2608.18084v1 Announce Type: new Abstract: Theorem proving in real-world Lean 4 projects is challenging because proofs often depend on project-specific context. While iterative refinement can use compiler errors to repair failed proofs, reusing failed attempts requires careful search control: some proofs provide better starting points than others, and later revisions may…

--
Équipe
1 min
Lire l'article