Copertina

CFSafety: Comprehensive Fine-grained Safety Assessment for LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Zhihao, Hu, Chenhui
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring Vulnerabilities and Protections in Large Language Models: A Survey
di: Liu, Frank Weizhen, et al.
Pubblicazione: (2024)

Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning
di: Jan, Essa, et al.
Pubblicazione: (2024)

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
di: Nikitin, Alexander, et al.
Pubblicazione: (2024)

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety
di: Guan, Zihan, et al.
Pubblicazione: (2025)

Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
di: Kim, Seungone, et al.
Pubblicazione: (2023)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
di: Chu, Junjie, et al.
Pubblicazione: (2024)

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

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

LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs
di: Zhou, Yujun, et al.
Pubblicazione: (2024)

A Framework to Implement 1+N Multi-task Fine-tuning Pattern in LLMs Using the CGC-LORA Algorithm
di: Song, Chao, et al.
Pubblicazione: (2024)

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
di: Zhou, Huichi, et al.
Pubblicazione: (2025)

XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection
di: Yang, Yuanhang, et al.
Pubblicazione: (2024)

Automated Data Enrichment using Confidence-Aware Fine-Grained Debate among Open-Source LLMs for Mental Health and Online Safety
di: Mao, Junyu, et al.
Pubblicazione: (2025)

LongSafety: Enhance Safety for Long-Context LLMs
di: Huang, Mianqiu, et al.
Pubblicazione: (2024)

Bypassing Safety Guardrails in LLMs Using Humor
di: Cisneros-Velarde, Pedro
Pubblicazione: (2025)

QEFT: Quantization for Efficient Fine-Tuning of LLMs
di: Lee, Changhun, et al.
Pubblicazione: (2024)

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
di: Wang, Guoli, et al.
Pubblicazione: (2026)

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
di: Weng, Jiaqi, et al.
Pubblicazione: (2025)

Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
di: Yang, Xikang, et al.
Pubblicazione: (2025)

Always Tell Me The Odds: Fine-grained Conditional Probability Estimation
di: Wang, Liaoyaqi, et al.
Pubblicazione: (2025)

Read the Scene, Not the Script: Outcome-Aware Safety for LLMs
di: Wu, Rui, et al.
Pubblicazione: (2025)

Topic Modeling with Fine-tuning LLMs and Bag of Sentences
di: Schneider, Johannes
Pubblicazione: (2024)

MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing
di: Li, Jiaqi, et al.
Pubblicazione: (2024)

What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
di: Jain, Samyak, et al.
Pubblicazione: (2024)

Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety
di: Shen, Qian, et al.
Pubblicazione: (2026)

PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs
di: Peng, Dan, et al.
Pubblicazione: (2024)

Objective Matters: Fine-Tuning Objectives Shape Safety, Robustness, and Persona Drift
di: Vennemeyer, Daniel, et al.
Pubblicazione: (2026)

CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning
di: Liu, Peiyuan, et al.
Pubblicazione: (2024)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
di: Siu, Vincent, et al.
Pubblicazione: (2025)

MolReFlect: Towards In-Context Fine-grained Alignments between Molecules and Texts
di: Li, Jiatong, et al.
Pubblicazione: (2024)

BlockDialect: Block-wise Fine-grained Mixed Format Quantization for Energy-Efficient LLM Inference
di: Jang, Wonsuk, et al.
Pubblicazione: (2025)

Certifying Knowledge Comprehension in LLMs
di: Chaudhary, Isha, et al.
Pubblicazione: (2024)

Simplify-This: A Comparative Analysis of Prompt-Based and Fine-Tuned LLMs
di: Cohen, Eilam, et al.
Pubblicazione: (2026)

SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation
di: Kamel, Rafiq, et al.
Pubblicazione: (2025)

Learning to Stay Safe: Adaptive Regularization Against Safety Degradation during Fine-Tuning
di: Goel, Jyotin, et al.
Pubblicazione: (2026)

DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
di: Wang, Minzheng, et al.
Pubblicazione: (2024)

Aligning Large Language Models via Fine-grained Supervision
di: Xu, Dehong, et al.
Pubblicazione: (2024)

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
di: Wang, Xu, et al.
Pubblicazione: (2025)

When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective
di: Zhang, Zelin, et al.
Pubblicazione: (2026)

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
di: Asif, Sadia, et al.
Pubblicazione: (2026)