Results 1 to 10 of about 4,127,736 (370)
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis [PDF]
arXiv.org, 2023 Recent text-to-image generative models can generate high-fidelity images from text inputs, but the quality of these generated images cannot be accurately evaluated by existing evaluation metrics.
Xiaoshi Wu +6 more
semanticscholar +1 more source
Diffusion Model Alignment Using Direct Preference Optimization [PDF]
Computer Vision and Pattern Recognition, 2023 Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been widely
Bram Wallace +9 more
semanticscholar +1 more source
Statistical Rejection Sampling Improves Preference Optimization [PDF]
International Conference on Learning Representations, 2023 Improving the alignment of language models with human preferences remains an active research challenge. Previous approaches have primarily utilized Reinforcement Learning from Human Feedback (RLHF) via online RL methods such as Proximal Policy ...
Tianqi Liu +6 more
semanticscholar +1 more source
Preference Ranking Optimization for Human Alignment [PDF]
AAAI Conference on Artificial Intelligence, 2023 Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human feedback (RLHF) has been employed to achieve this alignment.
Feifan Song +6 more
semanticscholar +1 more source
User Preference-aware Fake News Detection [PDF]
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021 Disinformation and fake news have posed detrimental effects on individuals and society in recent years, attracting broad attention to fake news detection.
Yingtong Dou +4 more
semanticscholar +1 more source
Patient advocacy group involvement in health technology assessments: an observational study
Research Involvement and Engagement, 2021 Plain English summary What are health technology assessments? Health technologies are medicines, devices and services used to prevent, diagnose or treat medical conditions.
Ann Single +5 more
doaj +1 more source
Current Status of Studies Measuring Health State Utility for 121 Rare Diseases
罕见病研究, 2023 Pharmacoeconomic evaluation is the essential supporting information for the inclusion of rare disease drugs into medical insurance in China. The accurate measurement of the health state utility of rare diseas is of practical significance to the ...
FENG Junchao +5 more
doaj +1 more source
Frontiers in Oncology, 2022 ObjectiveWe aimed to investigate the cost-effectiveness of nivolumab plus chemotherapy and nivolumab plus ipilimumab versus chemotherapy in the first-line treatment for advanced esophageal squamous-cell carcinoma (ESCC) patients from a healthcare system ...
Shixian Liu +23 more
doaj +1 more source
Frontiers in Pharmacology, 2023 Objective: This study was aimed to investigate the cost-effectiveness of all available programmed death 1 (PD-1) inhibitors combined with chemotherapy in the first-line treatment of advanced esophageal squamous-cell carcinoma (ESCC) from the Chinese ...
Shixian Liu +8 more
doaj +1 more source
Frontiers in Immunology, 2023 ObjectiveThe ASTRUM-007 trial (NCT03958890) demonstrated that serplulimab plus chemotherapy administered every 2-week significantly improved progression-free and overall survival in patients with previously untreated, programmed death-ligand 1 (PD-L1 ...
Shixian Liu +9 more
doaj +1 more source