Imagen de Portada

Understanding Annotator Safety Policy with Interpretability

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Oesterling, Alex, Ren, Donghao, Assogba, Yannick, Moritz, Dominik, Kim, Sunnie S. Y., Gatys, Leon, Hohman, Fred
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments
por: Boggust, Angie, et al.
Publicado: (2024)

Evaluating Long Range Dependency Handling in Code Generation LLMs
por: Assogba, Yannick, et al.
Publicado: (2024)

Exploring Empty Spaces: Human-in-the-Loop Data Augmentation
por: Yeh, Catherine, et al.
Publicado: (2024)

Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences
por: Hohman, Fred, et al.
Publicado: (2023)

A Scalable Approach to Clustering Embedding Projections
por: Ren, Donghao, et al.
Publicado: (2025)

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
por: Krishna, Kundan, et al.
Publicado: (2025)

Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language
por: Boggust, Angie, et al.
Publicado: (2025)

Embedding Atlas: Low-Friction, Interactive Embedding Visualization
por: Ren, Donghao, et al.
Publicado: (2025)

Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers
por: Oesterling, Alex, et al.
Publicado: (2024)

Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors
por: Lam, Michelle S., et al.
Publicado: (2024)

Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
por: Bhalla, Usha, et al.
Publicado: (2025)

Fair Machine Unlearning: Data Removal while Mitigating Disparities
por: Oesterling, Alex, et al.
Publicado: (2023)

VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety
por: Palaskar, Shruti, et al.
Publicado: (2025)

Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference
por: Hohman, Fred, et al.
Publicado: (2024)

Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates
por: Prakash, Nikhil, et al.
Publicado: (2025)

EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts
por: Mukherjee, Kushin, et al.
Publicado: (2025)

PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
por: Deng, Wesley Hanwen, et al.
Publicado: (2025)

APRIL: Annotations for Policy evaluation with Reliable Inference from LLMs
por: Mandyam, Aishwarya, et al.
Publicado: (2025)

Understanding and Preserving Safety in Fine-Tuned LLMs
por: Zhang, Jiawen, et al.
Publicado: (2026)

Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
por: Feng, Jingyuan, et al.
Publicado: (2026)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
por: Li, Changming, et al.
Publicado: (2026)

Interpretable Policy Distillation for Power Grid Topology Control
por: Dmitruka, Aleksandra, et al.
Publicado: (2026)

Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning
por: Kohler, Hector, et al.
Publicado: (2024)

Pragmatic Policy Development via Interpretable Behavior Cloning
por: Matsson, Anton, et al.
Publicado: (2025)

Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
por: Kohler, Hector, et al.
Publicado: (2025)

Annotation-Assisted Learning of Treatment Policies From Multimodal Electronic Health Records
por: Arno, Henri, et al.
Publicado: (2025)

An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
por: Park, Seonghwan, et al.
Publicado: (2025)

Reinforcement Learning with $ω$-Regular Objectives and Constraints
por: Wagner, Dominik, et al.
Publicado: (2025)

Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies
por: Rietz, Finn, et al.
Publicado: (2024)

Machine Learning for Climate Policy: Understanding Policy Progression in the European Green Deal
por: West, Patricia, et al.
Publicado: (2025)

Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation
por: Brunink, Yannick, et al.
Publicado: (2025)

Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning
por: Pravetz, Thomas
Publicado: (2026)

Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks
por: Graf, Peter, et al.
Publicado: (2024)

Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications
por: Lee, Yoon Pyo
Publicado: (2025)

SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control
por: Liao, Xiao-Cheng, et al.
Publicado: (2025)

Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning
por: Deuschel, Jannik, et al.
Publicado: (2023)

How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning
por: Weltevrede, Max, et al.
Publicado: (2025)

Identifying Intervenable and Interpretable Features via Orthogonality Regularization
por: Miller, Moritz, et al.
Publicado: (2026)

PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
por: Deng, Wesley Hanwen, et al.
Publicado: (2026)

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
por: Pan, Licheng, et al.
Publicado: (2025)