# The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs

arXiv: https://arxiv.org/abs/2510.07775 · HTML: https://mlsanity.com/paper/2510.07775/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 28 of 28)

- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions](https://mlsanity.com/paper/2309.07875/) (2023)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates](https://mlsanity.com/paper/2402.18540/) (2024)
- [Representation Noising: A Defence Mechanism Against Harmful Finetuning](https://mlsanity.com/paper/2405.14577/) (2024)
- [Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation](https://mlsanity.com/paper/2409.01586/) (2024)
- [TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space](https://mlsanity.com/paper/2402.17811/) (2024)
- [Model Organisms for Emergent Misalignment](https://mlsanity.com/paper/2506.11613/) (2025)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)
- [Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning](https://mlsanity.com/paper/2507.16795/) (2025)
- [Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese](https://mlsanity.com/paper/2402.17302/) (2024)
- [HALoGEN: Fantastic LLM Hallucinations and Where to Find Them](https://mlsanity.com/paper/2501.08292/) (2025)
- [Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency](https://mlsanity.com/paper/2506.17209/) (2025)
- [Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment](https://mlsanity.com/paper/2507.18631/) (2025)
- [Rethinking Safety in LLM Fine-tuning: An Optimization Perspective](https://mlsanity.com/paper/2508.12531/) (2025)
- [Gradient Surgery for Safe LLM Fine-Tuning](https://mlsanity.com/paper/2508.07172/) (2025)
- [Secure LLM Fine-Tuning via Safety-Aware Probing](https://mlsanity.com/paper/2505.16737/) (2025)
- [A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations](https://mlsanity.com/paper/2507.23221/) (2025)
- [HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models](https://mlsanity.com/paper/2503.12908/) (2025)
- [From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models](https://mlsanity.com/paper/2505.24232/) (2025)

## Built on by (most cited first, 2 of 2)

- [MUCnoHARM@GermEval Shared Task 2026: Retrieval-based In-Context Learning for Defamatory Offences, and Where It Falls Short](https://mlsanity.com/paper/2609.09791/) (2026)
- [DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs](https://mlsanity.com/paper/2609.28570/) (2026)

## Abstract (arXiv)

Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing truthfulness can negatively impact safety alignment. In this paper, we investigate this trade-off and show that increasing factual accuracy often comes at the cost of weakened refusal behavior. Our analysis reveals that this arises from overlapping components in the model that simultaneously encode hallucination and refusal information, leading alignment methods to suppress factual knowledge unintentionally. We further examine how fine-tuning on benign datasets, even when curated for safety, can degrade alignment for the same reason. To address this, we propose a method that disentangles refusal-related features from hallucination features using sparse autoencoders, and preserves refusal behavior during fine-tuning through subspace orthogonalization. This approach prevents hallucinations from increasing while maintaining safety alignment.We evaluate our method on commonsense reasoning tasks and harmful benchmarks (AdvBench and StrongReject). Results demonstrate that our approach preserves refusal behavior and task utility, mitigating the trade-off between truthfulness and safety.