# Cross-Task Defense: Instruction-Tuning LLMs for Content Safety

arXiv: https://arxiv.org/abs/2405.15202 · HTML: https://mlsanity.com/paper/2405.15202/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 18 references that are in the map.
- First posted on arXiv 24 May 2024.

## Builds on (most cited first, 15 of 15)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation](https://mlsanity.com/paper/2310.06987/) (2023)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [Identifying and Mitigating the Security Risks of Generative AI](https://mlsanity.com/paper/2308.14840/) (2023)
- [Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues](https://mlsanity.com/paper/2402.09091/) (2024)
- [Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack](https://mlsanity.com/paper/2312.06924/) (2023)

## Built on by (most cited first, 8 of 8)

- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs](https://mlsanity.com/paper/2406.06622/) (2024)
- [Recent Advances in Attack and Defense Approaches of Large Language Models](https://mlsanity.com/paper/2409.03274/) (2024)
- [Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation](https://mlsanity.com/paper/2503.06519/) (2025)
- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)
- [Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond](https://mlsanity.com/paper/2410.18114/) (2024)
- [From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop](https://mlsanity.com/paper/2608.11171/) (2026)
- [Visual Grounding Safety in Vision-Language Models](https://mlsanity.com/paper/2610.05637/) (2026)

## Abstract (arXiv)

Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization and translation. Despite defenses against malicious short questions, the ability of LLMs to safely handle dangerous long content, such as manuals teaching illicit activities, remains unclear. Our work aims to develop robust defenses for LLMs in processing malicious documents alongside benign NLP task queries. We introduce a defense dataset comprised of safety-related examples and propose single-task and mixed-task losses for instruction tuning. Our empirical results demonstrate that LLMs can significantly enhance their capacity to safely manage dangerous content with appropriate instruction tuning. Additionally, strengthening the defenses of tasks most susceptible to misuse is effective in protecting LLMs against processing harmful information. We also observe that trade-offs between utility and safety exist in defense strategies, where Llama2, utilizing our proposed approach, displays a significantly better balance compared to Llama1.