# Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior

arXiv: https://arxiv.org/abs/2503.17882 · HTML: https://mlsanity.com/paper/2503.17882/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 25 of its 25 references that are in the map.
- First posted on arXiv 22 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 25 of 25)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [The Falcon Series of Open Language Models](https://mlsanity.com/paper/2311.16867/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://mlsanity.com/paper/2212.08061/) (2022)
- [Recipes for Safety in Open-domain Chatbots](https://mlsanity.com/paper/2010.07079/) (2020)
- [Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking](https://mlsanity.com/paper/2311.09827/) (2023)
- [Self-Guard: Empower the LLM to Safeguard Itself](https://mlsanity.com/paper/2310.15851/) (2023)
- [SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering](https://mlsanity.com/paper/2408.11491/) (2024)
- [Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation](https://mlsanity.com/paper/2410.03415/) (2024)
- [Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation](https://mlsanity.com/paper/2110.08501/) (2021)
- [AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability](https://mlsanity.com/paper/2402.09404/) (2024)

## Built on by (most cited first, 12 of 12)

- [Reasoning as an Adaptive Defense for Safety](https://mlsanity.com/paper/2507.00971/) (2025)
- [CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention](https://mlsanity.com/paper/2509.06982/) (2025)
- [Read the Scene, Not the Script: Outcome-Aware Safety for LLMs](https://mlsanity.com/paper/2510.04320/) (2025)
- [Reasoning Up the Instruction Ladder for Controllable Language Models](https://mlsanity.com/paper/2511.04694/) (2025)
- [Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs](https://mlsanity.com/paper/2510.08158/) (2025)
- [Dynamic Evaluation for Oversensitivity in LLMs](https://mlsanity.com/paper/2510.19005/) (2025)
- [DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair](https://mlsanity.com/paper/2606.03601/) (2026)
- [SHARD: Safe and Helpful Alignment via Self-Reframing Distillation](https://mlsanity.com/paper/2606.15517/) (2026)
- [Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models](https://mlsanity.com/paper/2606.16808/) (2026)
- [Addressing Over-Refusal in LLMs with Competing Rewards](https://mlsanity.com/paper/2606.31748/) (2026)
- [Pretraining Curricula Enable Selective Fine-tuning](https://mlsanity.com/paper/2607.04846/) (2026)
- [Making Your LLMs More Objective: Stabilizing LLM Safety Behavior Across Traits with Trait-Invariant Safety Tuning](https://mlsanity.com/paper/2608.11705/) (2026)

## Abstract (arXiv)

Recent advancements in large language models (LLMs) have demonstrated that fine-tuning and human alignment can render LLMs harmless. In practice, such "harmlessness" behavior is mainly achieved by training models to reject harmful requests, such as "Explain how to burn down my neighbor's house", where the model appropriately declines to respond. However, this approach can inadvertently result in false refusal, where models reject benign queries as well, such as "Tell me how to kill a Python process". In this work, we demonstrate that prompting safety reflection before generating a response can mitigate false refusal behavior. Building on this finding, we introduce the Think-Before-Refusal (TBR) schema and conduct safety-aware instruction fine-tuning incorporating safety reflection. In an ablation study across 15 pre-trained models, we show that models fine-tuned with safety reflection significantly reduce false refusal behavior while maintaining safety and overall performance compared to those fine-tuned without safety reflection.