English
Related papers

Related papers: FigCaps-HF: A Figure-to-Caption Generative Framewo…

200 papers

While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: perception-induced errors that propagate through the…

Multimedia · Computer Science 2025-09-29 Songjun Tu , Qichao Zhang , Jingbo Sun , Yuqian Fu , Linjing Li , Xiangyuan Lan , Dongmei Jiang , Yaowei Wang , Dongbin Zhao

Large Language Models (LLMs) fine-tuned via Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) significantly improve the alignment of human-AI values, further raising the upper bound…

Artificial Intelligence · Computer Science 2025-10-10 Jian Hu , Xibin Wu , Wei Shen , Jason Klein Liu , Zilin Zhu , Weixun Wang , Songlin Jiang , Haoran Wang , Hao Chen , Bin Chen , Weikai Fang , Xianyu , Yu Cao , Haotian Xu , Yiming Liu

Humor is a commonly used and intricate human language in daily life. Humor generation, especially in multi-modal scenarios, is a challenging task for large language models (LLMs), which is typically as funny caption generation for images,…

Computation and Language · Computer Science 2026-02-09 Wenbo Shang , Yuxi Sun , Jing Ma , Xin Huang

Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignment is the strength of reward models used during training.…

Computation and Language · Computer Science 2024-10-17 Yanjun Chen , Dawei Zhu , Yirong Sun , Xinghao Chen , Wei Zhang , Xiaoyu Shen

Reinforcement Learning from Human/AI Feedback (RLHF/RLAIF) has been extensively utilized for preference alignment of text-to-image models. Existing methods face certain limitations in terms of both data and algorithm. For training data,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Xingyu Lu , Yuhang Hu , YiFan Zhang , Kaiyu Jiang , Changyi Liu , Tianke Zhang , Jinpeng Wang , Chun Yuan , Bin Wen , Fan Yang , Tingting Gao , Di Zhang

Human preferences are widely used to align large language models (LLMs) through methods such as reinforcement learning from human feedback (RLHF). However, the current user interfaces require annotators to compare text paragraphs, which is…

Human-Computer Interaction · Computer Science 2025-07-28 Danqing Shi , Furui Cheng , Tino Weinkauf , Antti Oulasvirta , Mennatallah El-Assady

The open-ended nature of visual captioning makes it a challenging area for evaluation. The majority of proposed models rely on specialized training to improve human-correlation, resulting in limited adoption, generalizability, and…

Computation and Language · Computer Science 2022-01-11 Joshua Feinglass , Yezhou Yang

Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Ying Ba , Tianyu Zhang , Yalong Bai , Wenyi Mo , Tao Liang , Bing Su , Ji-Rong Wen

Reinforcement learning from human feedback (RLHF) is a vital strategy for enhancing model capability in language models. However, annotating preference data for RLHF is a resource-intensive and creativity-demanding process, while existing…

Computation and Language · Computer Science 2024-04-02 Taiwei Shi , Kai Chen , Jieyu Zhao

Video captioning is a challenging task since it requires generating sentences describing various diverse and complex videos. Existing video captioning models lack adequate visual representation due to the neglect of the existence of gaps…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Mingkang Tang , Zhanyu Wang , Zhenhua Liu , Fengyun Rao , Dian Li , Xiu Li

We propose an approach for interactive learning for an image captioning model. As human feedback is expensive and modern neural network based approaches often require large amounts of supervised data to be trained, we envision a system that…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Mareike Hartmann , Aliki Anagnostopoulou , Daniel Sonntag

Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward…

Computation and Language · Computer Science 2023-05-18 Yao Zhao , Rishabh Joshi , Tianqi Liu , Misha Khalman , Mohammad Saleh , Peter J. Liu

Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. We coin the term \textit{Learned…

Machine Learning · Computer Science 2025-09-22 Luke Marks , Amir Abdullah , Clement Neo , Rauno Arike , David Krueger , Philip Torr , Fazl Barez

Fine-tuning image captioning models with hand-crafted rewards like the CIDEr metric has been a classical strategy for promoting caption quality at the sequence level. This approach, however, is known to limit descriptiveness and semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Nicholas Moratelli , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts toward Generative Reward Models (GenRMs) that generate…

Current captioning approaches tend to generate correct but "generic" descriptions that lack real-world knowledge, e.g., named entities and contextual information. Considering that Vision-Language Pre-Training (VLP) models master massive…

Computer Vision and Pattern Recognition · Computer Science 2023-08-03 Kanzhi Cheng , Wenpo Song , Zheng Ma , Wenhao Zhu , Zixuan Zhu , Jianbing Zhang

Uniform-reward reinforcement learning from human feedback (RLHF), which trains a single reward model to represent the preferences of all annotators, fails to capture the diversity of opinions across sub-populations, inadvertently favoring…

Machine Learning · Computer Science 2025-09-05 Arpan Mukherjee , Marcello Bullo , Deniz Gündüz

Reinforcement learning from human feedback (RLHF) has contributed to performance improvements in large language models. To tackle its reliance on substantial amounts of human-labeled data, a successful approach is multi-task representation…

Machine Learning · Computer Science 2025-03-06 Ruitao Chen , Liwei Wang

In recent years, advancements in representation learning and language models have propelled Automated Captioning (AC) to new heights, enabling the generation of human-level descriptions. Leveraging these advancements, we propose AVCap, an…

Audio and Speech Processing · Electrical Eng. & Systems 2024-07-12 Jongsuk Kim , Jiwon Shin , Junmo Kim

Recent multimodal large language models have shown promising ability in generating humorous captions for images, yet they still lack stable control over explicit cultural context, making it difficult to jointly maintain image relevance,…

Computation and Language · Computer Science 2026-04-21 Run Xu , Lu Li , Rongzhao Zhang , Jie Xu