paper-with-me

홈 › Papers

PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection

2025-09-30 · Tuan Nguyen, Naseem Khan, Khang Tran, NhatHai Phan, Issa Khalil arxiv

The rapid rise of synthetic media has made deepfake detection a critical challenge for online safety and trust. Progress remains constrained by the scarcity of large, high-quality datasets. Although multimodal large language models (LLMs) exhibit strong reasoning capabilities, their performance on deepfake detection is poor, often producing explanations that are misaligned with visual evidence or hallucinatory. To address this limitation, we introduce a reasoning-annotated dataset for deepfake detection and propose Paragraph-level Relative Policy Optimization (PRPO), a reinforcement learning algorithm that aligns LLM reasoning with image content at the paragraph level. Experiments show that PRPO improves detection accuracy by a wide margin and achieves the highest reasoning score of 4.55/5.0. Ablation studies further demonstrate that PRPO significantly outperforms GRPO under test-time conditions. These results underscore the importance of grounding multimodal reasoning in visual evidence to enable more reliable and interpretable deepfake detection.

📄 PDF Abstract BibTeX arXiv:2509.26272

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningMultimodal ReasoningDeepFake Detection

Similar Papers 제목 키워드 기반

PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization

2026-01-12 · Ruiyi Ding, Yongxuan Lv, Xianhui Meng, Jiahe Song 외 arxiv

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limit…

PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping

2026-06-07 · Qiming Li, Tianlun Li, Xiaolong Cheng, Hangyu Li 외 arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective paradigm for improving the reasoning capability of Large Vision-Language Models (LVLMs). However, existing RLVR methods primarily rely on traj…

Reinforcement LearningMultimodal Reasoning

Proximal Ranking Policy Optimization for Practical Safety in Counterfactual Learning to Rank

2024-09-15 · Shashank Gupta, Harrie Oosterhuis, Maarten de Rijke

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse p…

counterfactualLearning-To-Rank

Practical and Robust Safety Guarantees for Advanced Counterfactual Learning to Rank

2024-07-29 · Shashank Gupta, Harrie Oosterhuis, Maarten de Rijke

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse p…

counterfactualLearning-To-Rank

Mitigating Preference Hacking in Policy Optimization with Pessimism

2025-03-10 · Dhawal Gupta, Adam Fisch, Christoph Dann, Alekh Agarwal

This work tackles the problem of overoptimization in reinforcement learning from human feedback (RLHF), a prevalent technique for aligning models with human preferences. RLHF relies on reward or preference models trained…

Document Summarization