Intelligence Artificielle - Blog

🧠

Intelligence Artificielle

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

arXiv:2608.14629v1 Announce Type: new Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI). Current model alignment paradigms, such as reinforcement learning…

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review

arXiv:2608.14626v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-resource and multilingual settings than in high-resource languages. In this paper, we conduct a Systematic Literature Review (SLR) of LLM safety alignment in low-resource languages…

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search

arXiv:2608.14621v1 Announce Type: new Abstract: Long-term memory is increasingly central to LLM agents, yet memory design remains a highly coupled architecture problem: what to encode, how to store it, how to retrieve it, and how to manage it can vary substantially across tasks and backbone models. We construct a discrete search space with 5 encoders, 5 stores, 6 retrievers,…

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

Wiola 13M, a Gated Spiral Attention Architecture for Parameter Efficient Small Language Models

arXiv:2608.14604v1 Announce Type: new Abstract: Small language models in the ten to one hundred million parameter range are attractive for on device inference, rapid experimentation, and controlled scientific study, yet most of them reuse the standard transformer block without adaptation to the small scale regime. We present Wiola, a decoder only language model whose novelty…

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

Multi-Modal Generative Fuzzy System: Fuzzy Inference Guided Large Model Interactive Question Answering Framework

arXiv:2608.14584v1 Announce Type: new Abstract: In Multimodal Question Answering (MQA), models are required to jointly encode and integrate heterogeneous information from multiple modalities, including text, images, and speech, to perform complex semantic reasoning and decision making. Despite recent advances, existing approaches, including traditional deep learning models…

--

Équipe

1 min

Lire l'article

🧠

Intelligence Artificielle

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

arXiv:2608.14577v1 Announce Type: new Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently, little is known about the harmful outputs produced during model misbehavior, partly because large-scale, high-quality collections of frontier-LLM misbehavior are…

--

Équipe

1 min

Lire l'article

Restez à la pointe de la tech

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review

AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search

Wiola 13M, a Gated Spiral Attention Architecture for Parameter Efficient Small Language Models

Multi-Modal Generative Fuzzy System: Fuzzy Inference Guided Large Model Interactive Question Answering Framework

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs