Imagen de Portada

The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Doku, Ronald
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward
por: An, Hao, et al.
Publicado: (2025)

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
por: Machcha, Sravanthi, et al.
Publicado: (2026)

Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
por: Heng, Alvin, et al.
Publicado: (2025)

When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
por: Zhou, Xinyu, et al.
Publicado: (2026)

Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?
por: Gaus, Johannes A., et al.
Publicado: (2026)

Do not Abstain! Identify and Solve the Uncertainty
por: Liu, Jingyu, et al.
Publicado: (2025)

Abstaining Machine Learning -- Philosophical Considerations
por: Schuster, Daniela
Publicado: (2024)

Interpretable and Fair Mechanisms for Abstaining Classifiers
por: Lenders, Daphne, et al.
Publicado: (2025)

Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
por: Guan, Xiaoliu, et al.
Publicado: (2025)

Confident Feature Ranking
por: Neuhof, Bitya, et al.
Publicado: (2023)

LLMs Should Not Yet Be Credited with Decision Explanation
por: Wang, Wenshuo
Publicado: (2026)

CAMEL: Confidence-Gated Reflection for Reward Modeling
por: Zhu, Zirui, et al.
Publicado: (2026)

CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
por: Sun, Yuxi, et al.
Publicado: (2025)

The Confidence Paradox: Can LLM Know When It's Wrong
por: Tripathi, Sahil, et al.
Publicado: (2025)

Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
por: Baan, Joris, et al.
Publicado: (2026)

Epistemic Filtering and Collective Hallucination: A Jury Theorem for Confidence-Calibrated Agents
por: Karge, Jonas
Publicado: (2026)

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making
por: Liu, Jun, et al.
Publicado: (2026)

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
por: Zhai, Skylar, et al.
Publicado: (2026)

Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
por: Wang, Hongru, et al.
Publicado: (2025)

Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate
por: Zheng, Liangwei Nathan, et al.
Publicado: (2025)

Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
por: Jin, Gaojie, et al.
Publicado: (2026)

Robot Metacognition: Decision Making with Confidence for Tool Invention
por: Meera, Ajith Anil, et al.
Publicado: (2025)

When Should Algorithms Resign? A Proposal for AI Governance
por: Bhatt, Umang, et al.
Publicado: (2024)

Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions
por: Liu, Junzhang, et al.
Publicado: (2024)

When Quantization Affects Confidence of Large Language Models?
por: Proskurina, Irina, et al.
Publicado: (2024)

Modeling User Exploration Saturation: When Recommender Systems Should Stop Pushing Novelty
por: Ayiku, Enock O., et al.
Publicado: (2026)

Should XAI Nudge Human Decisions with Explanation Biasing?
por: Fukuchi, Yosuke, et al.
Publicado: (2024)

PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
por: Leang, Joshua Ong Jun, et al.
Publicado: (2025)

Clustered Policy Decision Ranking
por: Levin, Mark, et al.
Publicado: (2023)

Adaptive Confidence Gating in Multi-Agent Collaboration for Efficient and Optimized Code Generation
por: Zhang, Haoji, et al.
Publicado: (2026)

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
por: Sheng, Leheng, et al.
Publicado: (2026)

When Should an AI Workflow Release? Always-Valid Inference for Black-Box Generate-Verify Systems
por: Cho, Young Hyun, et al.
Publicado: (2026)

When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO
por: Li, Yu, et al.
Publicado: (2026)

Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?
por: Omori, Yumi, et al.
Publicado: (2025)

Large Language Models Should Ask Clarifying Questions to Increase Confidence in Generated Code
por: Wu, Jie JW
Publicado: (2023)

Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores
por: Balkır, Esma, et al.
Publicado: (2026)

Confidence-Aware Decision-Making and Control for Tool Selection
por: Meera, Ajith Anil, et al.
Publicado: (2024)

When to Act: Calibrated Confidence for Reliable Human Intention Prediction in Assistive Robotics
por: Gaus, Johannes A., et al.
Publicado: (2026)

MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision
por: Zheng, Hongjie, et al.
Publicado: (2025)

PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
por: Pulipaka, Sidharth, et al.
Publicado: (2026)