Image de couverture de livre

When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Nagireddy, Manish, Padhi, Inkit, Ghosh, Soumya, Sattigeri, Prasanna
Format:	Preprint
Publié:	2024
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

Value Alignment from Unstructured Text
par: Padhi, Inkit, et autres
Publié: (2024)

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
par: Huang, Yue, et autres
Publié: (2025)

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
par: Gourabathina, Abinitha, et autres
Publié: (2026)

Contextual Moral Value Alignment Through Context-Based Aggregation
par: Dognin, Pierre, et autres
Publié: (2024)

Language Models in Dialogue: Conversational Maxims for Human-AI Interactions
par: Miehling, Erik, et autres
Publié: (2024)

Programming Refusal with Conditional Activation Steering
par: Lee, Bruce W., et autres
Publié: (2024)

Thermometer: Towards Universal Calibration for Large Language Models
par: Shen, Maohao, et autres
Publié: (2024)

WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
par: Hou, Yufang, et autres
Publié: (2024)

Large Language Model Confidence Estimation via Black-Box Access
par: Pedapati, Tejaswini, et autres
Publié: (2024)

Multi-Level Explanations for Generative Language Models
par: Paes, Lucas Monteiro, et autres
Publié: (2024)

Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
par: Achintalwar, Swapnaja, et autres
Publié: (2024)

Granite Guardian
par: Padhi, Inkit, et autres
Publié: (2024)

Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
par: Kadhe, Swanand Ravindra, et autres
Publié: (2024)

Building Guardrails for Large Language Models
par: Dong, Yi, et autres
Publié: (2024)

Mapping Clinical Doubt: Locating Linguistic Uncertainty in LLMs
par: Sridhar, Srivarshinee, et autres
Publié: (2025)

Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing
par: Baldini, Ioana, et autres
Publié: (2023)

Extending Beacon to Hindi: Cultural Adaptation Drives Cross-Lingual Sycophancy
par: Sattigeri, Sarthak
Publié: (2026)

Graph-based Uncertainty Metrics for Long-form Language Model Outputs
par: Jiang, Mingjian, et autres
Publié: (2024)

When in Doubt, Consult: Expert Debate for Sexism Detection via Confidence-Based Routing
par: Alajmi, Anwar, et autres
Publié: (2025)

WebGuard: Building a Generalizable Guardrail for Web Agents
par: Zheng, Boyuan, et autres
Publié: (2025)

Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness
par: Gupta, Ashim, et autres
Publié: (2023)

Guardrail Baselines for Unlearning in LLMs
par: Thaker, Pratiksha, et autres
Publié: (2024)

Cascaded Information Disclosure for Generalized Evaluation of Problem Solving Capabilities
par: Yan, Yunxiang, et autres
Publié: (2025)

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
par: Akgül, Ömer Faruk, et autres
Publié: (2026)

Protect: Towards Robust Guardrailing Stack for Trustworthy Enterprise LLM Systems
par: Avinash, Karthik, et autres
Publié: (2025)

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
par: Wei, Dennis, et autres
Publié: (2024)

SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening
par: Nahin, Shahriar Kabir, et autres
Publié: (2026)

Small Updates, Big Doubts: Does Parameter-Efficient Fine-tuning Enhance Hallucination Detection ?
par: Hu, Xu, et autres
Publié: (2026)

Revisiting Overthinking in Long Chain-of-Thought from the Perspective of Self-Doubt
par: Peng, Keqin, et autres
Publié: (2025)

Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
par: Ghosh, Shaona, et autres
Publié: (2025)

OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models
par: Wang, Thomas, et autres
Publié: (2025)

RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
par: She, Yining, et autres
Publié: (2025)

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
par: Lee, Seanie, et autres
Publié: (2025)

The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers
par: Mozannar, Hussein, et autres
Publié: (2024)

Benchmarking LLM Guardrails in Handling Multilingual Toxicity
par: Yang, Yahan, et autres
Publié: (2024)

Triaging Threats to Specialized Guardrails
par: Mo, Wenjie Jacky, et autres
Publié: (2026)

CTG-KrEW: Generating Synthetic Structured Contextually Correlated Content by Conditional Tabular GAN with K-Means Clustering and Efficient Word Embedding
par: Samanta, Riya, et autres
Publié: (2024)

A Causal Explainable Guardrails for Large Language Models
par: Chu, Zhixuan, et autres
Publié: (2024)

Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
par: Shen, Maohao, et autres
Publié: (2024)

Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution
par: Wang, Ante, et autres
Publié: (2025)