Imagen de Portada

Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policies

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Mittal, Avni
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Did You Forget What I Asked? Prospective Memory Failures in Large Language Models
por: Mittal, Avni
Publicado: (2026)

Can LLMs Follow Simple Rules?
por: Mu, Norman, et al.
Publicado: (2023)

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
por: Mayne, Harry, et al.
Publicado: (2025)

Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
por: Jeong, Hyejun, et al.
Publicado: (2024)

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
por: Wang, Chenyang, et al.
Publicado: (2025)

PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
por: Gokden, Burc
Publicado: (2025)

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning
por: Mittal, Avni, et al.
Publicado: (2026)

LongSafety: Enhance Safety for Long-Context LLMs
por: Huang, Mianqiu, et al.
Publicado: (2024)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
por: Siu, Vincent, et al.
Publicado: (2025)

Is In-Context Learning Sufficient for Instruction Following in LLMs?
por: Zhao, Hao, et al.
Publicado: (2024)

Training Language Models to Explain Their Own Computations
por: Li, Belinda Z., et al.
Publicado: (2025)

Language Models Can Predict Their Own Behavior
por: Ashok, Dhananjay, et al.
Publicado: (2025)

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
por: Choi, Yunho, et al.
Publicado: (2026)

Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA
por: Agarwal, Dhruv, et al.
Publicado: (2023)

Do Multilingual LLMs Think In English?
por: Schut, Lisa, et al.
Publicado: (2025)

Why Do Safety Guardrails Degrade Across Languages?
por: Zhang, Max, et al.
Publicado: (2026)

Efficient Safety Retrofitting Against Jailbreaking for LLMs
por: Garcia-Gasulla, Dario, et al.
Publicado: (2025)

FALCON: Autonomous Cyber Threat Intelligence Mining with LLMs for IDS Rule Generation
por: Mitra, Shaswata, et al.
Publicado: (2025)

Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
por: Yang, Xikang, et al.
Publicado: (2025)

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
por: Ren, Richard, et al.
Publicado: (2024)

Do LLMs Encode Functional Importance of Reasoning Tokens?
por: Singh, Janvijay, et al.
Publicado: (2026)

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
por: Wei, Boyi, et al.
Publicado: (2024)

De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules
por: Guliani, Keerat, et al.
Publicado: (2026)

Multilingual Safety Alignment via Self-Distillation
por: Qin, Ruiyang, et al.
Publicado: (2026)

How Likely Do LLMs with CoT Mimic Human Reasoning?
por: Bao, Guangsheng, et al.
Publicado: (2024)

Transformer-Squared: Self-adaptive LLMs
por: Sun, Qi, et al.
Publicado: (2025)

(How) Do Language Models Track State?
por: Li, Belinda Z., et al.
Publicado: (2025)

Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning
por: Jan, Essa, et al.
Publicado: (2024)

Do LLMs Benefit From Their Own Words?
por: Huang, Jenny Y., et al.
Publicado: (2026)

Questionnaire Responses Do not Capture the Safety of AI Agents
por: Hellrigel-Holderbaum, Max, et al.
Publicado: (2026)

Rule by Rule: Learning with Confidence through Vocabulary Expansion
por: Nössig, Albert, et al.
Publicado: (2024)

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
por: Yang, Zhihe, et al.
Publicado: (2025)

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
por: Xu, Tianyang, et al.
Publicado: (2024)

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
por: Xi, Zhiheng, et al.
Publicado: (2025)

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
por: Xia, Wei, et al.
Publicado: (2026)

Auditing language models for hidden objectives
por: Marks, Samuel, et al.
Publicado: (2025)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
por: Chaudhary, Maheep, et al.
Publicado: (2025)

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
por: Wu, Xuansheng, et al.
Publicado: (2023)

Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions
por: Mohammadi, Seyedali, et al.
Publicado: (2025)

Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
por: Kim, Minsang, et al.
Publicado: (2026)