RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language Models

arXiv:2609.00790 · cs.CR · Submitted 2026-09-01 · Read on arXiv

cs.CR

Submitted: 2026-09-01

Updated: 2026-09-01

Code: https://github.com/ChangWenhan/RISA

Terminology

• Calibration — 52× in this paper · explained in 7 episodes
• Verifier — 26× in this paper · explained in 2 episodes
• Alignment — 17× in this paper · explained in 1 episode
• AUROC — 14× in this paper · explained in 2 episodes
• Accuracy — 13× in this paper · explained in 1 episode
• Abstention — 8× in this paper · explained in 1 episode
• Transformer — 8× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Verification — 7× in this paper · explained in 2 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Steering — 6× in this paper · explained in 2 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Activation Addition — 3× in this paper · explained in 1 episode
• Response Inspection and Selective Actions — 3× in this paper
• Correct Refusal Rate — 2× in this paper
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Linear probe — 2× in this paper · explained in 2 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Representation Engineering — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Activation Steering — 1× in this paper · explained in 4 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Decoding — 1× in this paper · explained in 1 episode
• Attack Success Rate — 1× in this paper
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Over-Refusal Rate — 1× in this paper
• Reward Function — 1× in this paper · explained in 2 episodes
• Safe Helpfulness Rate — 1× in this paper

Sources

• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Steering Language Models With Activation Engineering
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Fine-Tuning Language Models from Human Preferences
• A General Language Assistant as a Laboratory for Alignment
• Constitutional AI: Harmlessness from AI Feedback
• Representation Engineering: A Top-Down Approach to AI Transparency

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs