SteerCheck: Attribution Specificity and Alignment Leakage in Activation-Steering Audits

arXiv:2608.24335 · cs.CL · Submitted 2026-08-25 · Read on arXiv

cs.CL

Submitted: 2026-08-25

Updated: 2026-08-25

Terminology

• Alignment — 71× in this paper · explained in 1 episode
• Steering — 32× in this paper · explained in 2 episodes
• Exchangeability — 22× in this paper · explained in 2 episodes
• Accuracy — 16× in this paper · explained in 1 episode
• Calibration — 9× in this paper · explained in 7 episodes
• Sycophancy — 7× in this paper · explained in 4 episodes
• Activation Steering — 6× in this paper · explained in 4 episodes
• Provenance — 4× in this paper · explained in 4 episodes
• Core — 3× in this paper · explained in 2 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Activation Addition — 2× in this paper · explained in 1 episode
• Analyzer — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration Failure — 1× in this paper · explained in 2 episodes
• Fisher Information — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Understanding (Un)Reliability of Steering Vectors in Language Models
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• Gemma 3 Technical Report
• Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence
• Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
• Qwen2.5 Technical Report
• Analyzing the Generalization and Reliability of Steering Vectors
• Steering Language Models With Activation Engineering
• Qwen3 Technical Report
• Where Steering Signals Come From: Activation Source Selection in Activation Steering
• Representation Engineering: A Top-Down Approach to AI Transparency

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