Y Meng, M Xia, D Chen - arXiv preprint arXiv:2405.14734, 2024 - arxiv.org
Direct Preference Optimization (DPO) is a widely used offline preference optimization algorithm that reparameterizes reward functions in reinforcement learning from human …
Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon …
Large language models are known to hallucinate when faced with unfamiliar queries, but the underlying mechanism that govern how models hallucinate are not yet fully understood …
T Yu, H Zhang, Y Yao, Y Dang, D Chen, X Lu… - arXiv preprint arXiv …, 2024 - arxiv.org
Learning from feedback reduces the hallucination of multimodal large language models (MLLMs) by aligning them with human preferences. While traditional methods rely on labor …
Confidence estimation aiming to evaluate output trustability is crucial for the application of large language models (LLM), especially the black-box ones. Existing confidence estimation …
Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre- trained large language models (LLMs) and vision models through instruction tuning. Despite …
The remarkable advancements in Multimodal Large Language Models (MLLMs) have not rendered them immune to challenges, particularly in the context of handling deceptive …
Large Language Models (LLMs) are notorious for blending fact with fiction and generating non-factual content, known as hallucinations. To address this challenge, we propose an …
When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that …