Copertina

SafeMT: Multi-turn Safety for Multimodal Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Han, Dai, Juntao, Ji, Jiaming, Li, Haoran, Cai, Chengkun, Wen, Pengcheng, Chan, Chi-Min, Chen, Boyuan, Yang, Yaodong, Han, Sirui, Guo, Yike
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AM$^3$Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs
di: Zhu, Han, et al.
Pubblicazione: (2026)

ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs
di: Wen, Pengcheng, et al.
Pubblicazione: (2025)

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
di: Ji, Jiaming, et al.
Pubblicazione: (2024)

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
di: Ji, Jiaming, et al.
Pubblicazione: (2025)

SafeLawBench: Towards Safe Alignment of Large Language Models
di: Cao, Chuxue, et al.
Pubblicazione: (2025)

When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning
di: Fang, Sitong, et al.
Pubblicazione: (2025)

InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
di: Chen, Boyuan, et al.
Pubblicazione: (2025)

J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
di: Chan, Chi-Min, et al.
Pubblicazione: (2025)

What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning
di: Zhou, Yujin, et al.
Pubblicazione: (2026)

Generative RLHF-V: Learning Principles from Multi-modal Human Preference
di: Zhou, Jiayi, et al.
Pubblicazione: (2025)

Mitigating Deceptive Alignment via Self-Monitoring
di: Ji, Jiaming, et al.
Pubblicazione: (2025)

Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors
di: Wen, Pengcheng, et al.
Pubblicazione: (2026)

Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning
di: Bai, Hongbo, et al.
Pubblicazione: (2026)

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
di: Wang, Lichao, et al.
Pubblicazione: (2026)

Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
di: Ji, Jiaming, et al.
Pubblicazione: (2023)

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
di: Zhang, Borong, et al.
Pubblicazione: (2025)

Benchmarking Multi-National Value Alignment for Large Language Models
di: Shi, Weijie, et al.
Pubblicazione: (2025)

Sequence to Sequence Reward Modeling: Improving RLHF by Language Feedback
di: Zhou, Jiayi, et al.
Pubblicazione: (2024)

SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
di: Zhang, Ruiyang, et al.
Pubblicazione: (2025)

Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection
di: Yakun, Cui, et al.
Pubblicazione: (2025)

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
di: Dai, Juntao, et al.
Pubblicazione: (2024)

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
di: Dai, Josef, et al.
Pubblicazione: (2024)

Measuring Hong Kong Massive Multi-Task Language Understanding
di: Cao, Chuxue, et al.
Pubblicazione: (2025)

SafeDreamer: Safe Reinforcement Learning with World Models
di: Huang, Weidong, et al.
Pubblicazione: (2023)

Aligner: Efficient Alignment by Learning to Correct
di: Ji, Jiaming, et al.
Pubblicazione: (2024)

VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
di: Chen, Jiawei, et al.
Pubblicazione: (2026)

A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs
di: Zhang, Guoxi, et al.
Pubblicazione: (2025)

HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong
di: Han, Sirui, et al.
Pubblicazione: (2025)

Debate with Images: Detecting Deceptive Behaviors in Multimodal Large Language Models
di: Fang, Sitong, et al.
Pubblicazione: (2025)

SAE-V: Interpreting Multimodal Models for Enhanced Alignment
di: Lou, Hantao, et al.
Pubblicazione: (2025)

MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
di: Yang, Tianzhuo, et al.
Pubblicazione: (2026)

Language Models Resist Alignment: Evidence From Data Compression
di: Ji, Jiaming, et al.
Pubblicazione: (2024)

MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data
di: Zhu, Zhenghao, et al.
Pubblicazione: (2025)

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
di: Bu, Yuyan, et al.
Pubblicazione: (2026)

LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning
di: Shi, Weijie, et al.
Pubblicazione: (2025)

Enhance the Safety in Reinforcement Learning by ADRC Lagrangian Methods
di: Zhang, Mingxu, et al.
Pubblicazione: (2026)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
di: Zhang, Borong, et al.
Pubblicazione: (2025)

DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
di: Chan, Chi-Min, et al.
Pubblicazione: (2026)

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
di: Cao, Chuxue, et al.
Pubblicazione: (2025)

Automate Strategy Finding with LLM in Quant Investment
di: Kou, Zhizhuo, et al.
Pubblicazione: (2024)