No article text was recorded for this version.
inference-time safety steering
Version 1 of 120 papers24 conceptsfrozen 2026-10-04
Papers in this version
- Blog: SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs
- Blog: Safety Alignment Can Be Not Superficial With Explicit Safety Signals
- Blog: MetaSC: Test-Time Safety Specification Optimization for Language Models
- Blog: Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models
- Blog: Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level
- Blog: Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey
- Blog: Superficial Safety Alignment Hypothesis
- Blog: Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
- Blog: Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
- Blog: Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs
- Blog: Shape it Up! Restoring LLM Safety during Finetuning
- Blog: QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety
- Blog: SecCodePRM: A Process Reward Model for Code Security
- Blog: Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
- Blog: Frustratingly Easy Jailbreak of Large Language Models via Output Prefix Attacks
- Blog: Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
- Blog: Reinforcement Learning with Backtracking Feedback
- Blog: Backtracking Improves Generation Safety
- Blog: Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
- Blog: SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_inference_time_safety_steering_b989a5d6,
title = {inference-time safety steering},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/inference-time-safety-steering/rdr_b989a5d6e7d0432b9bba001dd922d38d},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_inference_time_safety_steering_b989a5d6_v1,
title = {inference-time safety steering},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/inference-time-safety-steering/rdr_b989a5d6e7d0432b9bba001dd922d38d/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}