Saved in:
Bibliographic Details
Main Authors: Li, Xuying, Li, Zhuo, Kosuga, Yuji, Bian, Victor
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.01923
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Large Language Models (LLMs) have demonstrated strong reasoning capabilities, but their safety under adversarial conditions remains a challenge. This study examines the impact of output length on the robustness of DeepSeek-R1, particularly in Forced Thinking scenarios. We analyze responses across various adversarial prompts and find that while longer outputs can improve safety through self-correction, certain attack types exploit extended generations. Our findings suggest that output length should be dynamically controlled to balance reasoning effectiveness and security. We propose reinforcement learning-based policy adjustments and adaptive token length regulation to enhance LLM safety.