Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Mahmoud, Omar, Khalil, Ali, Semage, Buddhika Laknath, Karimpanal, Thommen George, Rana, Santu
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Improving Multilingual Language Models by Aligning Representations through Steering
par: Mahmoud, Omar, et autres
Publié: (2025)

Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment
par: Hussonnois, Maxence, et autres
Publié: (2025)

ECoDe: A Sample-Efficient Method for Co-Design of Robotic Agents
par: Nagiredla, Kishan R., et autres
Publié: (2023)

Dynamic Policy Fusion for User Alignment Without Re-Interaction
par: Palattuparambil, Ajsal Shereef, et autres
Publié: (2024)

Leveraging Human Feedback for Semantically-Relevant Skill Discovery
par: Hussonnois, Maxence, et autres
Publié: (2026)

ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
par: Palattuparambil, Ajsal Shereef, et autres
Publié: (2026)

MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer
par: Palattuparambil, Ajsal Shereef, et autres
Publié: (2025)

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs
par: Kassem, Aly M., et autres
Publié: (2024)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
par: Wang, Yanbo, et autres
Publié: (2026)

Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs
par: Bossy, Thierry, et autres
Publié: (2025)

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
par: Zhang, Xiaoying, et autres
Publié: (2024)

GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
par: Wang, Yue, et autres
Publié: (2025)

Unintended Impacts of LLM Alignment on Global Representation
par: Ryan, Michael J., et autres
Publié: (2024)

ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs
par: Simhi, Adi, et autres
Publié: (2025)

Causal ATE Mitigates Unintended Bias in Controlled Text Generation
par: Madhavan, Rahul, et autres
Publié: (2023)

Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
par: Liao, Yiming, et autres
Publié: (2026)

Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning
par: Li, Ang, et autres
Publié: (2025)

A Concise Review of Hallucinations in LLMs and their Mitigation
par: Pulkundwar, Parth, et autres
Publié: (2025)

On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
par: Wen, Xueru, et autres
Publié: (2024)

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
par: Chang, Kai-Po, et autres
Publié: (2025)

Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs
par: Ding, Hanxing, et autres
Publié: (2024)

Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment
par: Nghiem, Huy, et autres
Publié: (2025)

On the Interplay of Human-AI Alignment,Fairness, and Performance Trade-offs in Medical Imaging
par: Luo, Haozhe, et autres
Publié: (2025)

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
par: Hahm, Dongyoon, et autres
Publié: (2025)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
par: Pan, Birong, et autres
Publié: (2025)

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
par: Sun, Zhongxiang, et autres
Publié: (2026)

Mitigating Hallucinations in Healthcare LLMs with Granular Fact-Checking and Domain-Specific Adaptation
par: Zeba, Musarrat, et autres
Publié: (2025)

Learning to Trust Your Feelings: Leveraging Self-awareness in LLMs for Hallucination Mitigation
par: Liang, Yuxin, et autres
Publié: (2024)

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
par: Lou, Xinyue, et autres
Publié: (2025)

FVA-RAG: Falsification-Verification Alignment for Mitigating Sycophantic Hallucinations
par: Ravishankara, Mayank
Publié: (2025)

Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
par: Xie, Zequn, et autres
Publié: (2026)

Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
par: Tomani, Christian, et autres
Publié: (2024)

Hallucination Detection and Hallucination Mitigation: An Investigation
par: Luo, Junliang, et autres
Publié: (2024)

Unintended Harms of Value-Aligned LLMs: Psychological and Empirical Insights
par: Choi, Sooyung, et autres
Publié: (2025)

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
par: Zhao, Weixiang, et autres
Publié: (2025)

DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation
par: Chen, Jennifer, et autres
Publié: (2025)

Pun Unintended: LLMs and the Illusion of Humor Understanding
par: Zangari, Alessandro, et autres
Publié: (2025)

FinTradeBench: A Financial Reasoning Benchmark for LLMs
par: Agrawal, Yogesh, et autres
Publié: (2026)

Diagnosing the Performance Trade-off in Moral Alignment: A Case Study on Gender Stereotypes
par: Liu, Guangliang, et autres
Publié: (2025)

Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMs
par: Chae, Kyubyung, et autres
Publié: (2025)