paper-with-me

Papers

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

2025-03-22 · Shengyun Si, Xinpeng Wang, Guangyao Zhai, Nassir Navab, Barbara Plank

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.

📄 PDF Abstract BibTeX arXiv:2503.17882

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Large Reasoning Models Learn Better Alignment from Flawed Thinking

2025-10-01 · ShengYun Peng, Eric Smith, Ivan Evtimov, Song Jiang 외 arxiv

Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased whe…

Reinforcement Learning

Do Thinking Tokens Help with Safety?

2026-06-23 · Narutatsu Ri, Abhishek Panigrahi, Sanjeev Arora arxiv

Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts. It is also generally believed that this more "deliberative" mode should improve alignme…

Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?

2025-10-07 · Qingyu Yin, Chak Tou Leong, Linyi Yang, Wenxuan Huang 외 arxiv

Large reasoning models (LRMs) with multi-step reasoning capabilities have shown remarkable problem-solving abilities, yet they exhibit concerning safety vulnerabilities that remain poorly understood. In this work, we inv…

DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair

2026-06-02 · Qinyan Zhou, Peixin Zhang, Jun Sun, Haonan Zhang 외 arxiv

While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that merely appear risky. We present DDOR (De…

ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives

2026-08-31 · Hoejoon Kwon, Byeonggeuk Lim, Kahyeon Kim, YoungBin Kim arxiv

Safety alignment is essential for deploying large language models, requiring systems to prevent harmful compliance while preserving helpfulness on benign requests. Activation steering offers a training-free inference-tim…