Imagen de Portada

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Peizheng, Wang, Jingyao, Qiang, Wenwen, Zhou, Jiahuan, Zheng, Changwen, Hua, Gang
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

COPO: Consistency-Aware Policy Optimization
por: Han, Jinghang, et al.
Publicado: (2025)

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
por: Wang, Jingyao, et al.
Publicado: (2026)

Rethinking Multi-Modal Learning from Gradient Uncertainty
por: Guo, Peizheng, et al.
Publicado: (2025)

PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
por: Guo, Peizheng, et al.
Publicado: (2026)

Understanding Token-level Topological Structures in Transformer-based Time Series Forecasting
por: Zhang, Jianqi, et al.
Publicado: (2024)

On the Universality of Self-Supervised Learning
por: Qiang, Wenwen, et al.
Publicado: (2024)

BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
por: Li, Jiangmeng, et al.
Publicado: (2024)

Causally-Enhanced Reinforcement Policy Optimization
por: Wang, Xiangqi, et al.
Publicado: (2025)

Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning
por: Zhang, Jianqi, et al.
Publicado: (2026)

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations
por: Li, Shuo, et al.
Publicado: (2025)

Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration
por: Guo, Huijie, et al.
Publicado: (2025)

Affordance Benchmark for MLLMs
por: Wang, Junying, et al.
Publicado: (2025)

Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning
por: Tang, Jingyao, et al.
Publicado: (2025)

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?
por: Yin, Hao, et al.
Publicado: (2025)

Online Causal Kalman Filtering for Stable and Effective Policy Optimization
por: He, Shuo, et al.
Publicado: (2026)

HARP: Hallucination Detection via Reasoning Subspace Projection
por: Hu, Junjie, et al.
Publicado: (2025)

Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation
por: Wang, Jingyao, et al.
Publicado: (2025)

Look Within, Why LLMs Hallucinate: A Causal Perspective
por: Li, He, et al.
Publicado: (2024)

Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs
por: Ye, Hengwei, et al.
Publicado: (2026)

Rethinking Meta-Learning from a Learning Lens
por: Wang, Jingyao, et al.
Publicado: (2024)

Mitigating Hallucinations in Large Language Models via Causal Reasoning
por: Li, Yuangang, et al.
Publicado: (2025)

CIP: A Plug-and-Play Causal Prompting Framework for Mitigating Hallucinations under Long-Context Noise
por: Ma, Qingsen, et al.
Publicado: (2025)

DCPO: Dynamic Clipping Policy Optimization
por: Yang, Shihui, et al.
Publicado: (2025)

From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities
por: Jiang, Shixin, et al.
Publicado: (2024)

Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification?
por: Lin, Fei, et al.
Publicado: (2025)

Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
por: Nguyen, Vy, et al.
Publicado: (2025)

Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
por: Li, Yihan, et al.
Publicado: (2025)

A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery
por: Sng, Grace, et al.
Publicado: (2024)

Causal Discovery and Counterfactual Reasoning to Optimize Persuasive Dialogue Policies
por: Zeng, Donghuo, et al.
Publicado: (2025)

Redundancy Principles for MLLMs Benchmarks
por: Zhang, Zicheng, et al.
Publicado: (2025)

A Novel Differential Feature Learning for Effective Hallucination Detection and Classification
por: Wang, Wenkai, et al.
Publicado: (2025)

Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
por: Zhou, Yao, et al.
Publicado: (2026)

FaithLens: Detecting and Explaining Faithfulness Hallucination
por: Si, Shuzheng, et al.
Publicado: (2025)

Hallucination Detection-Guided Preference Optimization for Clinical Summarization
por: Seethakantha, Shamanth Kuthpadi, et al.
Publicado: (2026)

Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization
por: Khandoga, Mykola, et al.
Publicado: (2026)

GRIT: Teaching MLLMs to Think with Images
por: Fan, Yue, et al.
Publicado: (2025)

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking
por: Wang, Siyuan, et al.
Publicado: (2024)

Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models
por: Liu, Qiang, et al.
Publicado: (2025)

HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
por: Jiang, Xinyan, et al.
Publicado: (2025)

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
por: Choi, Yumin, et al.
Publicado: (2025)