No article text was recorded for this version.
contrastive safety fine-tuning
Version 1 of 123 papers26 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Can AI Assistants Know What They Don't Know?
- Blog: The Art of Saying No: Contextual Noncompliance in Language Models
- Blog: Fake Alignment: Are LLMs Really Aligned Well?
- Blog: Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models
- Blog: EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
- Blog: Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs
- Blog: Walking the Tightrope: Autonomous Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning
- Blog: Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
- Blog: Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions
- Blog: Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models
- Blog: Red Queen: Exposing Latent Multi-Turn Risks in Large Language Models
- Blog: LLM Safety Alignment is Divergence Estimation in Disguise
- Blog: Can a Large Language Model be a Gaslighter?
- Blog: Value Alignment from Unstructured Text
- Blog: SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
- Blog: Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
- Blog: What Do Safety-Aligned LLMs Learn From Mixed Compliance Demonstrations?
- Blog: POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization
- Blog: Can Video LLMs Refuse to Answer? Alignment for Answerability in Video Large Language Models
- Blog: Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
- Blog: CMD: a framework for Context-aware Model self-Detoxification
- Blog: Backtracking Improves Generation Safety
- Blog: WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_contrastive_safety_fine_tuning_b4b3885f,
title = {contrastive safety fine-tuning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/contrastive-safety-fine-tuning/rdr_b4b3885fcdde4e74a97aa8bd00d11cbc},
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_contrastive_safety_fine_tuning_b4b3885f_v1,
title = {contrastive safety fine-tuning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/contrastive-safety-fine-tuning/rdr_b4b3885fcdde4e74a97aa8bd00d11cbc/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}