conftrace_

safety alignment

178 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) adversarial attack (1621) model safety (101) harmful content (66) multimodal large language model (966) ai safety (235) language model (4599) llm safety (67) adversarial learning (1595)

Papers

SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models AAAI 2026

Unveiling AI Safety in Fine-tuning Quantized Model AAAI 2026

BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage EACL 2026

ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models AAAI 2026

Silenced Biases: The Dark Side LLMs Learned to Refuse AAAI 2026

Differentiated Directional Intervention: A Framework for Evading LLM Safety Alignment AAAI 2026

Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026

The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs EACL 2026

STAR-1: Safer Alignment of Reasoning LLMs with 1K Data AAAI 2026

Can Editing LLMs Inject Harm? AAAI 2026

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models AAAI 2026

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation AAAI 2026

EASE: Practical and Efficient Safety Alignment for Small Language Models AAAI 2026

HumorReject: Decoupling LLM Safety from Refusal Prefix via a Little Humor AAAI 2026

iMotion-LLM: Instruction-Conditioned Trajectory Generation WACV 2026

Layer-wise Swapping for Generalizable Multilingual Safety EACL 2026

IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages EACL 2026

Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models EACL 2026

Code-Switching as a Safety Failure Mode in Large Language Models: An Empirical Study of Roman Urdu across English, Mixed, and Transliteration-Only Inputs EACL 2026

A Simple and Efficient Learning-Style Prompting for LLM Jailbreaking EACL 2026

DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt AAAI 2026

Where to Start Alignment? Diffusion Large Language Model May Demand a Distinct Position AAAI 2026

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions AAAI 2026

When Safe Unimodal Inputs Collide: Optimizing Reasoning Chains for Cross-Modal Safety in Multimodal Large Language Models AAAI 2026

Rethinking Deep Alignment Through the Lens of Incomplete Safety Learning AAAI 2026