A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals

arXiv:2609.00760 · cs.CL · Submitted 2026-09-01 · Read on arXiv

cs.CL

Submitted: 2026-09-01

Updated: 2026-09-01

Terminology

• Alignment — 31× in this paper · explained in 1 episode
• Steering — 22× in this paper · explained in 2 episodes
• Ablation — 20× in this paper · explained in 1 episode
• Accuracy — 14× in this paper · explained in 1 episode
• Safety-Based Refusal — 13× in this paper
• Benchmark — 12× in this paper · explained in 2 episodes
• Grounding — 10× in this paper · explained in 3 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Verification — 6× in this paper · explained in 2 episodes
• Activation Steering — 5× in this paper · explained in 4 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Hallucination — 4× in this paper · explained in 4 episodes
• Knowledge-Based Refusal — 4× in this paper
• Robustness — 4× in this paper · explained in 5 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Regret — 3× in this paper · explained in 3 episodes
• Abstention — 2× in this paper · explained in 1 episode
• Epistemic Uncertainty — 2× in this paper · explained in 10 episodes
• Hallucination Mitigation — 2× in this paper · explained in 2 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Linear probe — 2× in this paper · explained in 2 episodes
• AUC — 1× in this paper · explained in 2 episodes
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Generalization — 1× in this paper · explained in 13 episodes
• LLM judge — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Understanding intermediate layers using linear classifier probes
• What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
• Training Verifiers to Solve Math Word Problems
• Qwen2.5 Technical Report
• The Llama 3 Herd of Models
• Measuring Massive Multitask Language Understanding
• OpenAI GPT-5 System Card
• Gemma 3 Technical Report
• Gemma 2: Improving Open Language Models at a Practical Size
• Universal and Transferable Adversarial Attacks on Aligned Language Models
• Steering Language Models With Activation Engineering
• Jailbreak Attacks and Defenses Against Large Language Models: A Survey
• FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering