Tous 676 🔐 Cybersécurité 417 🤖 Intelligence Artificielle 253 💻 Tech & Transformation Digitale 6
Chargement…
🧠
Intelligence Artificielle

Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMs

arXiv:2608.26123v1 Announce Type: new Abstract: Large language models (LLMs) are trained predominantly on English-language internet text that over-represents certain cultural narratives, raising concerns that models flatten the diversity of non-Western storytelling traditions into a single homogenized archetype. We present a pilot computational study examining this across…

Lire l'article
🧠
Intelligence Artificielle

Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention

arXiv:2608.26121v1 Announce Type: new Abstract: Large language models state false facts as fluently as true ones, yet a model often "knows" internally when it is on shaky ground: the probability it assigns to its own answer tends to dip on the facts it gets wrong. The usual way to act on this, teaching a model to abstain rather than guess, requires a labelled dataset of right…

Lire l'article
🧠
Intelligence Artificielle

Recipes for Steering and Scaling LLMs via Sampling

arXiv:2608.26120v1 Announce Type: new Abstract: Large Language Models (LLMs) are probabilistic models, typically defined by an autoregressive factorization. While recent work has begun to study richer target distributions beyond the base model, the sampling strategies remain highly inefficient. In this paper, we present a flexible and theoretically grounded framework for…

Lire l'article
🧠
Intelligence Artificielle

DeflectBench: A Benchmark for Evaluating Rhetorical Fallacy Generation in LLMs

arXiv:2608.26119v1 Announce Type: new Abstract: Whether large language models can be prompted to generate rhetorical fallacies on demand, and whether current safety post-training constrains this behavior, has received less attention than the related question of detecting fallacies in existing text. We close this gap with DeflectBench, evaluating 23,990 generations from four…

Lire l'article
🧠
Intelligence Artificielle

ElementCheck: Complexity-Aware Long-Form Text Factuality Evaluation via Sentence Elements

arXiv:2608.26118v1 Announce Type: new Abstract: Existing long-form factuality evaluation relies on the decompose-retrieve-verify pipeline. However, the pipeline suffers from noise from claim decomposition and fixed verification granularity, resulting in unreliable results. We propose ElementCheck, a complexity-aware framework that verifies long-form outputs via sentence…

Lire l'article
🧠
Intelligence Artificielle

TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding

arXiv:2608.26112v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference through a draft-then-verify paradigm. Building on this, tree-structured methods improve inference by organizing proposals into multiple candidate paths, increasing the accepted length. However, existing tree-structured methods use a single drafter for all drafting…

Lire l'article