Image de couverture de livre

Do Language Models Know When They'll Refuse? Probing Introspective Awareness of Safety Boundaries

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Gondil, Tanay
Format:	Preprint
Publié:	2026
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

When Two LLMs Debate, Both Think They'll Win
par: Prasad, Pradyumna Shyama, et autres
Publié: (2025)

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
par: Pan, Wenbo, et autres
Publié: (2025)

Do Retrieval Augmented Language Models Know When They Don't Know?
par: Zhou, Youchao, et autres
Publié: (2025)

Emergent Introspective Awareness in Large Language Models
par: Lindsey, Jack
Publié: (2026)

From Imitation to Introspection: Probing Self-Consciousness in Language Models
par: Chen, Sirui, et autres
Publié: (2024)

Do Language Models Know When They're Hallucinating References?
par: Agrawal, Ayush, et autres
Publié: (2023)

Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models
par: Madhusudhan, Nishanth, et autres
Publié: (2024)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
par: Mei, Zhiting, et autres
Publié: (2025)

STAIR: Improving Safety Alignment with Introspective Reasoning
par: Zhang, Yichi, et autres
Publié: (2025)

Refusal Direction is Universal Across Safety-Aligned Languages
par: Wang, Xinpeng, et autres
Publié: (2025)

When Safety Blocks Sense: Measuring Semantic Confusion in LLM Refusals
par: Anonto, Riad Ahmed, et autres
Publié: (2025)

Do LVLMs Know What They Know? A Systematic Study of Knowledge Boundary Perception in LVLMs
par: Ding, Zhikai, et autres
Publié: (2025)

Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing
par: Zhao, Raoyuan, et autres
Publié: (2025)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
par: Ferrando, Javier, et autres
Publié: (2024)

Thinking Out Loud: Do Reasoning Models Know When They're Right?
par: Zeng, Qingcheng, et autres
Publié: (2025)

Language Models Fail to Introspect About Their Knowledge of Language
par: Song, Siyuan, et autres
Publié: (2025)

Large Language Models Know What To Say But Not When To Speak
par: Umair, Muhammad, et autres
Publié: (2024)

Where Do Reasoning Models Refuse?
par: Yamaguchi, Kureha, et autres
Publié: (2025)

Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations
par: Wang, Haoran, et autres
Publié: (2026)

Do Large Language Models Know How Much They Know?
par: Prato, Gabriele, et autres
Publié: (2025)

When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
par: Hadeliya, Tsimur, et autres
Publié: (2025)

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
par: Zhang, Yue, et autres
Publié: (2026)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
par: Abdaljalil, Samir, et autres
Publié: (2026)

Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
par: Duan, Ranjie, et autres
Publié: (2025)

Do Large Language Models Know What They Are Capable Of?
par: Barkan, Casey O., et autres
Publié: (2025)

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
par: McGovern, Hope, et autres
Publié: (2026)

Understanding Refusal in Language Models with Sparse Autoencoders
par: Yeo, Wei Jie, et autres
Publié: (2025)

Answer, Refuse, or Guess? Investigating Risk-Aware Decision Making in Language Models
par: Wu, Cheng-Kuang, et autres
Publié: (2025)

Do LLMs Know What Luxembourgish Borrows? Probing Lexical Neology in Low-Resource Multilingual Models
par: Hosseini-Kivanani, Nina
Publié: (2026)

Large Language Models Often Know When They Are Being Evaluated
par: Needham, Joe, et autres
Publié: (2025)

Knowing When to Ask -- Bridging Large Language Models and Data
par: Radhakrishnan, Prashanth, et autres
Publié: (2024)

Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
par: Si, Shengyun, et autres
Publié: (2025)

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models
par: Jain, Neel, et autres
Publié: (2024)

Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification
par: Zhang, Anqi, et autres
Publié: (2025)

Does It Make Sense to Speak of Introspection in Large Language Models?
par: Comsa, Iulia M., et autres
Publié: (2025)

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
par: Chae, Kyubyung, et autres
Publié: (2025)

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
par: Yuan, Youliang, et autres
Publié: (2024)

Language Specific Knowledge: Do Models Know Better in X than in English?
par: Agarwal, Ishika, et autres
Publié: (2025)

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
par: Muhamed, Aashiq, et autres
Publié: (2025)

Characterizing Selective Refusal Bias in Large Language Models
par: Khorramrouz, Adel, et autres
Publié: (2025)