Imagen de Portada

Confidence-Aware Alignment Makes Reasoning LLMs More Reliable

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Kejia, Zhang, Jiawen, Wu, Yihong, Gao, Kewei, Lou, Jian, Feng, Zunlei, Song, Mingli, Jia, Ruoxi
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

Token-Level Inference-Time Alignment for Vision-Language Models
por: Chen, Kejia, et al.
Publicado: (2025)

SHAPE : Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner
por: Chen, Kejia, et al.
Publicado: (2025)

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
por: Chen, Kejia, et al.
Publicado: (2026)

SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
por: Zhang, Jiawen, et al.
Publicado: (2025)

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models
por: Chen, Kejia, et al.
Publicado: (2025)

Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
por: Zhang, Jiawen, et al.
Publicado: (2025)

Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance
por: Zhang, Jiawen, et al.
Publicado: (2026)

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

Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework
por: Liu, Shunyu, et al.
Publicado: (2022)

Reinforced Model Merging
por: Han, Jiaqi, et al.
Publicado: (2025)

A Large-scale Universal Evaluation Benchmark For Face Forgery Detection
por: Bei, Yijun, et al.
Publicado: (2024)

Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
por: Sel, Bilgehan, et al.
Publicado: (2024)

Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework
por: Zhi, Zhuo, et al.
Publicado: (2025)

Adaptive Location Hierarchy Learning for Long-Tailed Mobility Prediction
por: Wang, Yu, et al.
Publicado: (2025)

Spatiotemporal-Augmented Graph Neural Networks for Human Mobility Simulation
por: Wang, Yu, et al.
Publicado: (2023)

Interaction Pattern Disentangling for Multi-Agent Reinforcement Learning
por: Liu, Shunyu, et al.
Publicado: (2022)

Knowledge Amalgamation for Object Detection with Transformers
por: Zhang, Haofei, et al.
Publicado: (2022)

Multiple Choice Questions: Reasoning Makes Large Language Models (LLMs) More Self-Confident, Especially When They are Wrong
por: Fu, Tairan, et al.
Publicado: (2025)

EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation
por: Shi, Jiahe, et al.
Publicado: (2025)

Calibration-Aware Policy Optimization for Reasoning LLMs
por: Wang, Ziqi, et al.
Publicado: (2026)

Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment
por: Su, Ruoxi, et al.
Publicado: (2026)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
por: Lu, Yuyin, et al.
Publicado: (2026)

A Comprehensive Study of Structural Pruning for Vision Models
por: Li, Changhao, et al.
Publicado: (2024)

$D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation
por: Wang, Ruizhi, et al.
Publicado: (2026)

AutoScale: Scale-Aware Data Mixing for Pre-Training LLMs
por: Kang, Feiyang, et al.
Publicado: (2024)

Efficient and Comprehensive Feature Extraction in Large Vision-Language Model for Pathology Analysis
por: Zhang, Shengxuming, et al.
Publicado: (2024)

Learning From Mistakes Makes LLM Better Reasoner
por: An, Shengnan, et al.
Publicado: (2023)

FASTTRACK: Fast and Accurate Fact Tracing for LLMs
por: Chen, Si, et al.
Publicado: (2024)

LLMs Can Plan Only If We Tell Them
por: Sel, Bilgehan, et al.
Publicado: (2025)

Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
por: Al-Tawaha, Ahmad, et al.
Publicado: (2026)

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice
por: Wang, Jiachen T., et al.
Publicado: (2025)

SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning
por: Liu, Huanyu, et al.
Publicado: (2025)

Towards Reliable, Uncertainty-Aware Alignment
por: Banerjee, Debangshu, et al.
Publicado: (2025)

Confidence as a Reward: Transforming LLMs into Reward Models
por: Du, He, et al.
Publicado: (2025)

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs
por: Qi, Shihao, et al.
Publicado: (2025)

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

Strategy-Aware Optimization Modeling with Reasoning LLMs
por: Zhao, Ruiqing, et al.
Publicado: (2026)

Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networks
por: Zhang, Jiaxing, et al.
Publicado: (2025)

The Signal is in the Steps: Local Scoring for Reasoning Data Selection
por: Just, Hoang Anh, et al.
Publicado: (2025)

Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation
por: Liu, Kejia, et al.
Publicado: (2026)