conftrace_

safe generation

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) language model (2) text-to-image generation (2) content moderation (2) toxic contrastive loss (1) token optimization (1) harmfulness detection (1) safety guidance (1) text to image (1) context-aware detoxification (1)

Papers

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router ACL 2026 SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers CVPR 2026 SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs ACL 2026 Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization CVPR 2025 Dialz: A Python Toolkit for Steering Vectors ACL 2025 CMD: a framework for Context-aware Model self-Detoxification EMNLP 2024 Universal Prompt Optimizer for Safe Text-to-Image Generation NAACL 2024 The CRINGE Loss: Learning what language not to model ACL 2023 Bot-Adversarial Dialogue for Safe Conversational Agents NAACL 2021