Cover Image

DARC: Disagreement-Aware Alignment via Risk-Constrained Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zou, Mingxi, Chen, Jiaxiang, Li, Junfan, Liang, Langzhang, Wang, Qifan, Yinghui, Xu, Xu, Zenglin
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making
by: Chen, Jiaxiang, et al.
Published: (2025)

From Implicit Exploration to Structured Reasoning: Leveraging Guideline and Refinement for LLMs
by: Chen, Jiaxiang, et al.
Published: (2025)

Guideline Forest: Retrieval-Augmented Reasoning with Branching Experience-Induced Guidelines
by: Chen, Jiaxiang, et al.
Published: (2025)

Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
by: Zou, Mingxi, et al.
Published: (2026)

IDInit: A Universal and Stable Initialization Method for Neural Network Training
by: Pan, Yu, et al.
Published: (2025)

FedCVD: The First Real-World Federated Learning Benchmark on Cardiovascular Disease Data
by: Zhang, Yukun, et al.
Published: (2024)

DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization
by: Sun, Xin, et al.
Published: (2024)

Tokenized Bandit for LLM Decoding and Alignment
by: Shin, Suho, et al.
Published: (2025)

Partial Differential Equations is All You Need for Generating Neural Architectures -- A Theory for Physical Artificial Intelligence Systems
by: Guo, Ping, et al.
Published: (2021)

Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
by: Li, Zhe, et al.
Published: (2023)

STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems
by: Bonagiri, Akash, et al.
Published: (2026)

IndexNet: Timestamp and Variable-Aware Modeling for Time Series Forecasting
by: Wu, Beiliang, et al.
Published: (2025)

ACE and Diverse Generalization via Selective Disagreement
by: Daniels, Oliver, et al.
Published: (2025)

Mitigating Spurious Correlations via Disagreement Probability
by: Han, Hyeonggeun, et al.
Published: (2024)

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
by: Lin, Baijiong, et al.
Published: (2025)

SlimRAG: Retrieval without Graphs via Entity-Aware Context Selection
by: Zhang, Jiale, et al.
Published: (2025)

Agreement-Constrained Probabilistic Minimum Bayes Risk Decoding
by: Natsumi, Koki, et al.
Published: (2025)

EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion
by: Berry, Lucas, et al.
Published: (2025)

Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
by: Wang, Mengxuan, et al.
Published: (2026)

Towards a Larger Model via One-Shot Federated Learning on Heterogeneous Client Models
by: Ye, Wenxuan, et al.
Published: (2025)

Uncertainty-Aware Decoding with Minimum Bayes Risk
by: Daheim, Nico, et al.
Published: (2025)

Speculative Safety-Aware Decoding
by: Wang, Xuekang, et al.
Published: (2025)

Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
by: Wang, Mingyi, et al.
Published: (2026)

Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
by: Liang, Langzhang, et al.
Published: (2025)

Sign is Not a Remedy: Multiset-to-Multiset Message Passing for Learning on Heterophilic Graphs
by: Liang, Langzhang, et al.
Published: (2024)

End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning
by: Chen, Guanzhong, et al.
Published: (2025)

PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
by: Zhang, Kaidong, et al.
Published: (2024)

BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
by: He, Liang, et al.
Published: (2026)

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk
by: Ying, Chengyang, et al.
Published: (2022)

Multi-Value Alignment for LLMs via Value Decorrelation and Extrapolation
by: Xu, Hefei, et al.
Published: (2025)

Towards User-level Private Reinforcement Learning with Human Feedback
by: Zhang, Jiaming, et al.
Published: (2025)

GeoPro-Net: Learning Interpretable Spatiotemporal Prediction Models through Statistically-Guided Geo-Prototyping
by: An, Bang, et al.
Published: (2024)

On the Necessity of Collaboration for Online Model Selection with Decentralized Data
by: Li, Junfan, et al.
Published: (2024)

A Polynomial-time Algorithm for Online Sparse Linear Regression with Improved Regret Bound under Weaker Conditions
by: Li, Junfan, et al.
Published: (2025)

LLM Safety Alignment is Divergence Estimation in Disguise
by: Haldar, Rajdeep, et al.
Published: (2025)

Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
by: Cao, Chentao, et al.
Published: (2025)

HIPO: Instruction Hierarchy via Constrained Reinforcement Learning
by: Chen, Keru, et al.
Published: (2026)

Graph Similarity Computation via Interpretable Neural Node Alignment
by: Wang, Jingjing, et al.
Published: (2024)

Enhancing Robustness of Offline Reinforcement Learning Under Data Corruption via Sharpness-Aware Minimization
by: Xu, Le, et al.
Published: (2025)

Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization
by: Wang, Dayu, et al.
Published: (2026)