Copertina

The Problem with Safety Classification is not just the Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Vajjala, Sowmya
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

IndicGEC: Powerful Models, or a Measurement Mirage?
di: Vajjala, Sowmya
Pubblicazione: (2025)

Text Classification in the LLM Era -- Where do we stand?
di: Vajjala, Sowmya, et al.
Pubblicazione: (2025)

MATA: Mindful Assessment of the Telugu Abilities of Large Language Models
di: Kranti, Chalamalasetti, et al.
Pubblicazione: (2025)

MetricalARGS: A Taxonomy for Studying Metrical Poetry with LLMs
di: Kranti, Chalamalasetti, et al.
Pubblicazione: (2025)

Does Synthetic Data Help Named Entity Recognition for Low-Resource Languages?
di: Kamath, Gaurav, et al.
Pubblicazione: (2025)

Dravidian language family through Universal Dependencies lens
di: Rama, Taraka, et al.
Pubblicazione: (2024)

Annotation Errors and NER: A Study with OntoNotes 5.0
di: Bernier-Colborne, Gabriel, et al.
Pubblicazione: (2024)

Scope Ambiguities in Large Language Models
di: Kamath, Gaurav, et al.
Pubblicazione: (2024)

Test Set Quality in Multilingual LLM Evaluation
di: Kranti, Chalamalasetti, et al.
Pubblicazione: (2025)

Opportunities and Challenges of LLMs in Education: An NLP Perspective
di: Vajjala, Sowmya, et al.
Pubblicazione: (2025)

LLMs in Education: Novel Perspectives, Challenges, and Opportunities
di: Alhafni, Bashar, et al.
Pubblicazione: (2024)

LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories
di: Vishnubhotla, Krishnapriya, et al.
Pubblicazione: (2026)

Making Metadata More FAIR Using Large Language Models
di: Sundaram, Sowmya S., et al.
Pubblicazione: (2023)

Are Emergent Abilities in Large Language Models just In-Context Learning?
di: Lu, Sheng, et al.
Pubblicazione: (2023)

CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors
di: Kadali, Sri Durga Sai Sowmya, et al.
Pubblicazione: (2025)

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models
di: Kadali, Sri Durga Sai Sowmya, et al.
Pubblicazione: (2026)

Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?
di: Kadali, Sri Durga Sai Sowmya, et al.
Pubblicazione: (2025)

Comparative Analysis of Transformer Models in Disaster Tweet Classification for Public Safety
di: Zisad, Sharif Noor, et al.
Pubblicazione: (2025)

Lightweight Safety Classification Using Pruned Language Models
di: Sawtell, Mason, et al.
Pubblicazione: (2024)

Translating speech with just images
di: Oneata, Dan, et al.
Pubblicazione: (2024)

Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework
di: Sun, Yuhong, et al.
Pubblicazione: (2025)

SafetyBench: Evaluating the Safety of Large Language Models
di: Zhang, Zhexin, et al.
Pubblicazione: (2023)

An Answer is just the Start: Related Insight Generation for Open-Ended Document-Grounded QA
di: Sharma, Saransh, et al.
Pubblicazione: (2026)

Classification of Safety Events at Nuclear Sites using Large Language Models
di: de Costa, Mishca, et al.
Pubblicazione: (2024)

UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment
di: Imperial, Joseph Marvin, et al.
Pubblicazione: (2025)

The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety
di: Rios-Sialer, Ian
Pubblicazione: (2026)

Sequential Classification of Aviation Safety Occurrences with Natural Language Processing
di: Nanyonga, Aziida, et al.
Pubblicazione: (2025)

ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts
di: Ukarapol, Trapoom, et al.
Pubblicazione: (2026)

Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models
di: In, Yeonjun, et al.
Pubblicazione: (2025)

Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
di: Lou, Xinyue, et al.
Pubblicazione: (2025)

Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
di: Zhao, Weixiang, et al.
Pubblicazione: (2024)

Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
di: Zhou, Xuhui, et al.
Pubblicazione: (2024)

KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models
di: Zaghouani, Wajdi, et al.
Pubblicazione: (2026)

Safety in Large Reasoning Models: A Survey
di: Wang, Cheng, et al.
Pubblicazione: (2025)

Mitigating Exaggerated Safety in Large Language Models
di: Ray, Ruchira, et al.
Pubblicazione: (2024)

Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models
di: Campregher, Dante, et al.
Pubblicazione: (2025)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
di: Hazra, Rima, et al.
Pubblicazione: (2024)

SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models
di: Vidgen, Bertie, et al.
Pubblicazione: (2023)

Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
di: Bianchi, Federico, et al.
Pubblicazione: (2023)

Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification
di: Weng, Charles, et al.
Pubblicazione: (2026)