# Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning

arXiv: https://arxiv.org/abs/2502.09673 · HTML: https://mlsanity.com/paper/2502.09673/

## Key facts

- Cited by 20 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 45 of its 60 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 30 of 45)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [Prompting Large Language Model for Machine Translation: A Case Study](https://mlsanity.com/paper/2301.07069/) (2023)
- [SafetyBench: Evaluating the Safety of Large Language Models](https://mlsanity.com/paper/2309.07045/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (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)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://mlsanity.com/paper/2305.03268/) (2023)
- [Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data](https://mlsanity.com/paper/2302.12822/) (2023)
- [What is in Your Safe Data? Identifying Benign Data that Breaks Safety](https://mlsanity.com/paper/2404.01099/) (2024)
- [Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2402.13950/) (2024)

## Built on by (most cited first, 20 of 20)

- [Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable](https://mlsanity.com/paper/2503.00555/) (2025)
- [Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers](https://mlsanity.com/paper/2506.15674/) (2025)
- [A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models](https://mlsanity.com/paper/2509.03871/) (2025)
- [Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency](https://mlsanity.com/paper/2510.21189/) (2025)
- [JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring](https://mlsanity.com/paper/2508.20848/) (2025)
- [VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models](https://mlsanity.com/paper/2505.19684/) (2025)
- [Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?](https://mlsanity.com/paper/2510.06036/) (2025)
- [THINKSAFE: Self-Generated Safety Alignment for Reasoning Models](https://mlsanity.com/paper/2601.23143/) (2026)
- [What Matters For Safety Alignment?](https://mlsanity.com/paper/2601.03868/) (2026)
- [LoRA is All You Need for Safety Alignment of Reasoning LLMs](https://mlsanity.com/paper/2507.17075/) (2025)
- [When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models](https://mlsanity.com/paper/2510.21285/) (2025)
- [Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs](https://mlsanity.com/paper/2511.00382/) (2025)
- [Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks](https://mlsanity.com/paper/2603.04459/) (2026)
- [Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models](https://mlsanity.com/paper/2602.02136/) (2026)
- [Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment](https://mlsanity.com/paper/2602.21346/) (2026)
- [SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training](https://mlsanity.com/paper/2603.02908/) (2026)
- [Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms](https://mlsanity.com/paper/2604.00012/) (2026)
- [TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models](https://mlsanity.com/paper/2606.00023/) (2026)
- [Safety Training May Persist Through Helpfulness Optimization in LLM Agents](https://mlsanity.com/paper/2603.02229/) (2026)
- [An Empirical Measurement of Jailbreaking Evaluators](https://mlsanity.com/paper/2609.10594/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs must reason, i.e., think logically, draw from past experiences, and synthesize information to reach conclusions and take action. To enhance reasoning abilities, approaches such as prompting and fine-tuning have been widely explored. While these methods have led to clear improvements in reasoning, their impact on LLM safety remains less understood. In this work, we investigate the interplay between reasoning and safety in LLMs. We highlight the latent safety risks that arise as reasoning capabilities improve, shedding light on previously overlooked vulnerabilities. At the same time, we explore how reasoning itself can be leveraged to enhance safety, uncovering potential mitigation strategies. By examining both the risks and opportunities in reasoning-driven LLM safety, our study provides valuable insights for developing models that are not only more capable but also more trustworthy in real-world deployments.