paper-with-me

Papers

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

2024-10-18 · Chenhang Cui, An Zhang, Yiyang Zhou, Zhaorun Chen, Gelei Deng, Huaxiu Yao, Tat-Seng Chua

The recent advancements in large language models (LLMs) and pre-trained vision models have accelerated the development of vision-language large models (VLLMs), enhancing the interaction between visual and linguistic modalities. Despite their notable success across various domains, VLLMs face challenges in modality alignment, which can lead to issues like hallucinations and unsafe content generation. Current alignment techniques often rely on coarse feedback and external datasets, limiting scalability and performance. In this paper, we propose FiSAO (Fine-Grained Self-Alignment Optimization), a novel self-alignment method that utilizes the model's own visual encoder as a fine-grained verifier to improve vision-language alignment without the need for additional data. By leveraging token-level feedback from the vision encoder, FiSAO significantly improves vision-language alignment, even surpassing traditional preference tuning methods that require additional data. Through both theoretical analysis and experimental validation, we demonstrate that FiSAO effectively addresses the misalignment problem in VLLMs, marking the first instance of token-level rewards being applied to such models.

📄 PDF Abstract BibTeX arXiv:2410.14148

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generative Verifiers: Reward Modeling as Next-Token Prediction

2024-08-27 · Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi 외

Verifiers or reward models are often used to enhance the reasoning performance of large language models (LLMs). A common approach is the Best-of-N method, where N candidate solutions generated by the LLM are ranked by a …

MathPredictionText Generation

Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation

2022-06-26 · Jiayan Guo, Peiyan Zhang, Chaozhuo Li, Xing Xie 외

Session-based recommendation (SBR) aims to predict the user next action based on the ongoing sessions. Recently, there has been an increasing interest in modeling the user preference evolution to capture the fine-grained…

Session-Based Recommendations

A Regret Minimization Framework on Preference Learning in Large Language Models

2026-06-08 · Suhwan Kim, Taehyun Cho, Geon-Hyeong Kim, Yu Jin Kim 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has enabled progress on reasoning-intensive tasks by relying on task-specific verifiers that provide automated correctness signals. However, many realistic language t…

Reinforcement LearningMathematical Reasoning

Learning Correlated Reward Models: Statistical Barriers and Opportunities

2025-10-17 · Yeshwanth Cherapanamjeri, Constantinos Daskalakis, Gabriele Farina, Sobhan Mohammadpour arxiv

Random Utility Models (RUMs) are a classical framework for modeling user preferences and play a key role in reward modeling for Reinforcement Learning from Human Feedback (RLHF). However, a crucial shortcoming of many of…

Reinforcement Learning

Self-Refining Video Sampling

2026-01-26 · Sangwon Jang, Taekyung Ki, Jaehyeong Jo, Saining Xie 외 arxiv

Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additional training on augmented data, which is…