Imagen de Portada

Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Ang, Mo, Yichuan, Li, Mingjie, Wang, Yifei, Wang, Yisen
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

Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
por: Wei, Zeming, et al.
Publicado: (2023)

Fight Back Against Jailbreaking via Prompt Adversarial Tuning
por: Mo, Yichuan, et al.
Publicado: (2024)

PID: Prompt-Independent Data Protection Against Latent Diffusion Models
por: Li, Ang, et al.
Publicado: (2024)

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms
por: Li, Mingjie, et al.
Publicado: (2026)

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models
por: Mo, Yichuan, et al.
Publicado: (2026)

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
por: Mo, Yichuan, et al.
Publicado: (2024)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
por: Chen, Taiye, et al.
Publicado: (2025)

Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
por: Wang, Yisen, et al.
Publicado: (2025)

Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
por: Chen, Hongyu, et al.
Publicado: (2025)

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
por: Wang, Zijun, et al.
Publicado: (2025)

Using LLMs for Automated Privacy Policy Analysis: Prompt Engineering, Fine-Tuning and Explainability
por: Chen, Yuxin, et al.
Publicado: (2025)

Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning
por: Pham, Anh, et al.
Publicado: (2025)

ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs
por: Thomas, Rohan Subramanian, et al.
Publicado: (2026)

Safety-Aware Fine-Tuning of Large Language Models
por: Choi, Hyeong Kyu, et al.
Publicado: (2024)

Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
por: Li, Wu, et al.
Publicado: (2026)

When More is Less: Understanding Chain-of-Thought Length in LLMs
por: Wu, Yuyang, et al.
Publicado: (2025)

G1: Teaching LLMs to Reason on Graphs with Reinforcement Learning
por: Guo, Xiaojun, et al.
Publicado: (2025)

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
por: An, Bang, et al.
Publicado: (2025)

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
por: Chen, Pin-Yu, et al.
Publicado: (2025)

DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism
por: Li, Dengchun, et al.
Publicado: (2025)

PAFT: Prompt-Agnostic Fine-Tuning
por: Wei, Chenxing, et al.
Publicado: (2025)

Rethinking Invariance in In-context Learning
por: Fang, Lizhe, et al.
Publicado: (2025)

Prior Prompt Engineering for Reinforcement Fine-Tuning
por: Taveekitworachai, Pittawat, et al.
Publicado: (2025)

Explore the Reasoning Capability of LLMs in the Chess Testbed
por: Wang, Shu, et al.
Publicado: (2024)

InvThink: Premortem Reasoning for Safer Language Models
por: Kim, Yubin, et al.
Publicado: (2025)

Informed Routing in LLMs: Smarter Token-Level Computation for Faster Inference
por: Han, Chao, et al.
Publicado: (2025)

Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs
por: Wang, Ruoyu, et al.
Publicado: (2024)

Prompting and Fine-Tuning of Small LLMs for Length-Controllable Telephone Call Summarization
por: Thulke, David, et al.
Publicado: (2024)

TsqLoRA: Towards Sensitivity and Quality Low-Rank Adaptation for Efficient Fine-Tuning
por: Chen, Yu, et al.
Publicado: (2025)

MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs
por: Lu, Zimu, et al.
Publicado: (2024)

Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning
por: Shernazarov, Ulugbek, et al.
Publicado: (2026)

RankAdaptor: Hierarchical Rank Allocation for Efficient Fine-Tuning Pruned LLMs via Performance Model
por: Zhou, Changhai, et al.
Publicado: (2024)

Selective Prompting Tuning for Personalized Conversations with LLMs
por: Huang, Qiushi, et al.
Publicado: (2024)

60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering
por: Ye, Junjie, et al.
Publicado: (2024)

LLMs for Explainable Business Decision-Making: A Reinforcement Learning Fine-Tuning Approach
por: Cheng, Xiang, et al.
Publicado: (2025)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
por: Wang, Yanbo, et al.
Publicado: (2026)

On the Adversarial Transferability of Generalized "Skip Connections"
por: Wang, Yisen, et al.
Publicado: (2024)

Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models
por: Sun, Haoyuan, et al.
Publicado: (2025)

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
por: Giordani, Jeremiah
Publicado: (2025)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
por: Pan, Birong, et al.
Publicado: (2025)