Buchumschlag

SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Diao, Muxi, Li, Rumei, Liu, Shiyang, Liao, Guogang, Wang, Jingang, Cai, Xunliang, Xu, Weiran
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
von: Wang, Yejie, et al.
Veröffentlicht: (2024)

Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models
von: Wang, Pei, et al.
Veröffentlicht: (2024)

Enhancing Safety of Large Language Models via Embedding Space Separation
von: Zhao, Xu, et al.
Veröffentlicht: (2026)

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
von: Wang, Yejie, et al.
Veröffentlicht: (2024)

S^3cMath: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners
von: Yan, Yuchen, et al.
Veröffentlicht: (2024)

Self-Evolving Critique Abilities in Large Language Models
von: Tang, Zhengyang, et al.
Veröffentlicht: (2025)

AgentRefine: Enhancing Agent Generalization through Refinement Tuning
von: Fu, Dayuan, et al.
Veröffentlicht: (2025)

Leveraging Large Language Models For Optimized Item Categorization using UNSPSC Taxonomy
von: Singh, Anmolika, et al.
Veröffentlicht: (2024)

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models
von: Yan, Siyu, et al.
Veröffentlicht: (2025)

NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation
von: Liu, Maoqi, et al.
Veröffentlicht: (2025)

Do Large Language Models Excel in Complex Logical Reasoning with Formal Language?
von: Jiang, Jin, et al.
Veröffentlicht: (2025)

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
von: Diao, Muxi, et al.
Veröffentlicht: (2026)

Automatic Instruction Evolving for Large Language Models
von: Zeng, Weihao, et al.
Veröffentlicht: (2024)

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery
von: Song, Xiaoshuai, et al.
Veröffentlicht: (2024)

Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
von: Zhang, Xuemiao, et al.
Veröffentlicht: (2025)

Adversarial Reinforcement Learning for Large Language Model Agent Safety
von: Wang, Zizhao, et al.
Veröffentlicht: (2025)

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
von: Zhang, Xuemiao, et al.
Veröffentlicht: (2025)

The Evolving Landscape of Generative Large Language Models and Traditional Natural Language Processing in Medicine
von: Yang, Rui, et al.
Veröffentlicht: (2025)

Evolving Subnetwork Training for Large Language Models
von: Li, Hanqi, et al.
Veröffentlicht: (2024)

The Information of Large Language Model Geometry
von: Tan, Zhiquan, et al.
Veröffentlicht: (2024)

Learning to Self-Verify Makes Language Models Better Reasoners
von: Chen, Yuxin, et al.
Veröffentlicht: (2026)

Learning to Self-Evolve
von: Chen, Xiaoyin, et al.
Veröffentlicht: (2026)

Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
von: Zhang, Qingru, et al.
Veröffentlicht: (2025)

Personalized Large Language Model Assistant with Evolving Conditional Memory
von: Yuan, Ruifeng, et al.
Veröffentlicht: (2023)

Automatic Adaptation Rule Optimization via Large Language Models
von: Ishimizu, Yusei, et al.
Veröffentlicht: (2024)

Scaling Embeddings Outperforms Scaling Experts in Language Models
von: Liu, Hong, et al.
Veröffentlicht: (2026)

Learning Evolving Tools for Large Language Models
von: Chen, Guoxin, et al.
Veröffentlicht: (2024)

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions
von: An, Shengnan, et al.
Veröffentlicht: (2025)

Language Models as Continuous Self-Evolving Data Engineers
von: Wang, Peidong, et al.
Veröffentlicht: (2024)

What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation
von: Gong, Zhuocheng, et al.
Veröffentlicht: (2024)

MDSF: Context-Aware Multi-Dimensional Data Storytelling Framework based on Large language Model
von: Zhang, Chengze, et al.
Veröffentlicht: (2025)

FinLLM-B: When Large Language Models Meet Financial Breakout Trading
von: Zhang, Kang, et al.
Veröffentlicht: (2024)

Self-Evolved Preference Optimization for Enhancing Mathematical Reasoning in Small Language Models
von: Singh, Joykirat, et al.
Veröffentlicht: (2025)

CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference
von: Yu, Erxin, et al.
Veröffentlicht: (2024)

Catching Chameleons: Detecting Evolving Disinformation Generated using Large Language Models
von: Jiang, Bohan, et al.
Veröffentlicht: (2024)

AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
von: Zhu, Zihao, et al.
Veröffentlicht: (2025)

General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
von: Liu, Junlin, et al.
Veröffentlicht: (2026)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
von: Liu, Zheyuan, et al.
Veröffentlicht: (2025)

Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop
von: Wang, Yaxuan, et al.
Veröffentlicht: (2026)

Cross-Platform Evaluation of Large Language Model Safety in Pediatric Consultations: Evolution of Adversarial Robustness and the Scale Paradox
von: Zolfaghari, Vahideh
Veröffentlicht: (2025)