Image de couverture de livre

Mitigating Exaggerated Safety in Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ray, Ruchira, Bhalani, Ruchi
Format:	Preprint
Publié:	2024
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

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
par: Röttger, Paul, et autres
Publié: (2023)

Defining Knowledge: Bridging Epistemology and Large Language Models
par: Fierro, Constanza, et autres
Publié: (2024)

Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs
par: Yuan, Shuzhou, et autres
Publié: (2025)

Evaluation Revisited: A Taxonomy of Evaluation Concerns in Natural Language Processing
par: Dhar, Ruchira, et autres
Publié: (2026)

Min-p, Max Exaggeration: A Critical Analysis of Min-p Sampling in Language Models
par: Schaeffer, Rylan, et autres
Publié: (2025)

RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation
par: James, Joseph, et autres
Publié: (2026)

Do Large Language Models Reflect Demographic Pluralism in Safety?
par: Naseem, Usman, et autres
Publié: (2026)

Hallucination Detection and Mitigation with Diffusion in Multi-Variate Time-Series Foundation Models
par: Wichitwechkarn, Vijja, et autres
Publié: (2025)

Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
par: Zhang, Junbo, et autres
Publié: (2025)

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

SafetyBench: Evaluating the Safety of Large Language Models
par: Zhang, Zhexin, et autres
Publié: (2023)

Diverse, but Divisive: LLMs Can Exaggerate Gender Differences in Opinion Related to Harms of Misinformation
par: Neumann, Terrence, et autres
Publié: (2024)

Mitigating the Bias of Large Language Model Evaluation
par: Zhou, Hongli, et autres
Publié: (2024)

From Words to Worlds: Compositionality for Cognitive Architectures
par: Dhar, Ruchira, et autres
Publié: (2024)

Mitigating Large Language Model Hallucination with Faithful Finetuning
par: Hu, Minda, et autres
Publié: (2024)

Exploring and Mitigating Fawning Hallucinations in Large Language Models
par: Shangguan, Zixuan, et autres
Publié: (2025)

Mitigating Label Length Bias in Large Language Models
par: Sanz-Guerrero, Mario, et autres
Publié: (2025)

When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
par: Mao, Yingzhi, et autres
Publié: (2025)

Do Multilingual Large Language Models Mitigate Stereotype Bias?
par: Nie, Shangrui, et autres
Publié: (2024)

Mitigating the Risk of Health Inequity Exacerbated by Large Language Models
par: Ji, Yuelyu, et autres
Publié: (2024)

Detection, Classification, and Mitigation of Gender Bias in Large Language Models
par: Cheng, Xiaoqing, et autres
Publié: (2025)

Mitigating Gambling-Like Risk-Taking Behaviors in Large Language Models: A Behavioral Economics Approach to AI Safety
par: Du, Y.
Publié: (2025)

Sycophancy in Large Language Models: Causes and Mitigations
par: Malmqvist, Lars
Publié: (2024)

An Evolutionary Large Language Model for Hallucination Mitigation
par: Boulesnane, Abdennour, et autres
Publié: (2024)

Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
par: Zhao, Weixiang, et autres
Publié: (2024)

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
par: In, Yeonjun, et autres
Publié: (2025)

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
par: Nie, Ercong, et autres
Publié: (2025)

Controlled Training Data Generation with Diffusion Models
par: Yeo, Teresa, et autres
Publié: (2024)

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
par: Liu, Qin, et autres
Publié: (2024)

Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing
par: Tran, Thien Q., et autres
Publié: (2025)

Evaluating Psychological Safety of Large Language Models
par: Li, Xingxuan, et autres
Publié: (2022)

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
par: Zhu, Didi, et autres
Publié: (2024)

Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives
par: Dhar, Ruchira, et autres
Publié: (2026)

KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models
par: Zaghouani, Wajdi, et autres
Publié: (2026)

LongSafety: Evaluating Long-Context Safety of Large Language Models
par: Lu, Yida, et autres
Publié: (2025)

Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models
par: Tong, Schrasing, et autres
Publié: (2024)

Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes
par: Nishida, Kosuke, et autres
Publié: (2024)

MBIAS: Mitigating Bias in Large Language Models While Retaining Context
par: Raza, Shaina, et autres
Publié: (2024)

A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
par: Tonmoy, S. M Towhidul Islam, et autres
Publié: (2024)

Unveiling and Mitigating Bias in Mental Health Analysis with Large Language Models
par: Wang, Yuqing, et autres
Publié: (2024)