Interpreting and Steering for Safe and Correct Code Generation
cs.AI
Submitted: 2026-08-30
Updated: 2026-08-30
Code: https://github.com/Ziyu-Yao-NLP-Lab/DuoSteer-Safe-Correct-Code-Gen
Terminology
Sources
- Mechanistic Interpretability for AI Safety -- A Review
- Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
- CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
- A Primer on the Inner Workings of Transformer-based Language Models
- The Llama 3 Herd of Models
- Instruction Tuning for Secure Code Generation
- CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs
- Qwen2.5-Coder Technical Report
- A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
- Activation Steering via Generative Causal Mediation
- Representation Engineering: A Top-Down Approach to AI Transparency
- Steering Language Models With Activation Engineering
- Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
- Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation
- SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection