Imagen de Portada

Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kumarappan, Adarsh, Mehrotra, Ayushi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Automating Deception: Scalable Multi-Turn LLM Jailbreaks
por: Kumarappan, Adarsh, et al.
Publicado: (2025)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
por: Robey, Alexander, et al.
Publicado: (2023)

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy
por: Kumarappan, Adarsh, et al.
Publicado: (2026)

DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models
por: Kumarappan, Adarsh, et al.
Publicado: (2026)

LeanAgent: Lifelong Learning for Formal Theorem Proving
por: Kumarappan, Adarsh, et al.
Publicado: (2024)

Probabilistic Stability Guarantees for Feature Attributions
por: Jin, Helen, et al.
Publicado: (2025)

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations
por: Marzari, Luca, et al.
Publicado: (2024)

Trust Regions for Explanations via Black-Box Probabilistic Certification
por: Dhurandhar, Amit, et al.
Publicado: (2024)

No Certificate for Alignment: Two Independent Impossibilities and the Pareto Frontier of Achievable Safety Guarantees
por: Agarwal, Ayushi
Publicado: (2026)

Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
por: Schnitzer, Yannik, et al.
Publicado: (2026)

Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change
por: Stępka, Ignacy, et al.
Publicado: (2024)

Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach
por: Han, Minghao, et al.
Publicado: (2026)

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
por: Marzari, Luca, et al.
Publicado: (2023)

Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
por: Maghsoudi, Maryam, et al.
Publicado: (2026)

Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments
por: Goodall, Alexander W., et al.
Publicado: (2024)

SimCert: Probabilistic Certification for Behavioral Similarity in Deep Neural Network Compression
por: Li, Jingyang, et al.
Publicado: (2026)

Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
por: Mehrotra, Anay, et al.
Publicado: (2026)

Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales
por: Nirmal, Ayushi, et al.
Publicado: (2024)

Anytime-Valid Answer Sufficiency Certificates for LLM Generation via Sequential Information Lift
por: Akter, Sanjeda, et al.
Publicado: (2025)

Toward Maturity-Based Certification of Embodied AI: Quantifying Trustworthiness Through Measurement Mechanisms
por: Darling, Michael C., et al.
Publicado: (2026)

Rational Tuning of LLM Cascades via Probabilistic Modeling
por: Zellinger, Michael J., et al.
Publicado: (2025)

Smooth InfoMax -- Towards Easier Post-Hoc Interpretability
por: Denoodt, Fabian, et al.
Publicado: (2024)

Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
por: Hamman, Faisal, et al.
Publicado: (2023)

How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluation
por: Singh, Prabhant, et al.
Publicado: (2025)

It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RL
por: Dwyer, Madeleine, et al.
Publicado: (2025)

Towards a Probabilistic Fusion Approach for Robust Battery Prognostics
por: Alcibar, Jokin, et al.
Publicado: (2024)

Towards Probabilistic Inductive Logic Programming with Neurosymbolic Inference and Relaxation
por: Hillerstrom, Fieke, et al.
Publicado: (2024)

GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots
por: Singh, Simranjit, et al.
Publicado: (2024)

FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning
por: Hu, Liang, et al.
Publicado: (2025)

CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
por: Wang, Zixia, et al.
Publicado: (2025)

Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting
por: Yao, Yueyang, et al.
Publicado: (2025)

Pushing Toward the Simplex Vertices: A Simple Remedy for Code Collapse in Smoothed Vector Quantization
por: Morita, Takashi
Publicado: (2025)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
por: Karvonen, Adam, et al.
Publicado: (2025)

Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNE
por: Ravuri, Aditya, et al.
Publicado: (2024)

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
por: Rasul, Kashif, et al.
Publicado: (2023)

A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
por: Zhang, Zegu, et al.
Publicado: (2026)

A Simplex Witness Certificate for Constant Collapse in Variational Autoencoders
por: Zhang, Zegu, et al.
Publicado: (2026)

Generalised Probabilistic Modelling and Improved Uncertainty Estimation in Comparative LLM-as-a-judge
por: Fathullah, Yassir, et al.
Publicado: (2025)

Certificate-Guided Pruning for Stochastic Lipschitz Optimization
por: Shihab, Ibne Farabi, et al.
Publicado: (2026)

Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques
por: Behera, Adarsh Prasad, et al.
Publicado: (2025)