SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically rely on post hoc filtering applied only to the final output, leaving intermediate reasoning steps unmonitored and vulnerable to adversarial manipulation. To address this gap, this paper proposes a SaFer Chain-of-Thought (SFCoT) framework, which proactively evalua
Record details
Published: 16 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Military & security
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Directional Embedding Smoothing for Robust Vision Language Models
arXiv · 16 March 2026
The Autonomy Tax: Defense Training Breaks LLM Agents
arXiv · 19 March 2026
Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking
arXiv · 7 March 2026
Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
arXiv · 6 March 2026
GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models
arXiv · 28 March 2026
Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
arXiv · 9 April 2026
How to cite this record
ethics.ai (16 March 2026), “SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration,” evidence record 7169, https://ethics.ai/record/7169 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.