Human-like object concept representations emerge naturally in multimodal large language models

C Du, K Fu, B Wen, Y Sun, J Peng, W Wei… - arXiv preprint arXiv …, 2024 - arxiv.org
The conceptualization and categorization of natural objects in the human mind have long
intrigued cognitive scientists and neuroscientists, offering crucial insights into human …

Camouflage Is All You Need: Evaluating and Enhancing Transformer Models Robustness Against Camouflage Adversarial Attacks

Á Huertas-García, A Martín… - … on Emerging Topics …, 2024 - ieeexplore.ieee.org
Advanced language models demonstrate remarkable capabilities but remain vulnerable to
adversarial word camouflage techniques. These techniques introduce visually perceptible …

Dual active learning for reinforcement learning from human feedback

P Liu, C Shi, WW Sun - arXiv preprint arXiv:2410.02504, 2024 - arxiv.org
Aligning large language models (LLMs) with human preferences is critical to recent
advances in generative artificial intelligence. Reinforcement learning from human feedback …

Investigating Context Effects in Similarity Judgements in Large Language Models

S Uprety, AK Jaiswal, H Liu, D Song - arXiv preprint arXiv:2408.10711, 2024 - arxiv.org
Large Language Models (LLMs) have revolutionised the capability of AI models in
comprehending and generating natural language text. They are increasingly being used to …