Imagen de Portada

Aligning Deep Implicit Preferences by Learning to Reason Defensively

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Peiming, Hu, Zhiyuan, Tang, Yang, Li, Shiyu, Chen, Xi
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
por: Lin, Dongding, et al.
Publicado: (2026)

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
por: Guo, Ping, et al.
Publicado: (2024)

AlignGroup: Learning and Aligning Group Consensus with Member Preferences for Group Recommendation
por: Xu, Jinfeng, et al.
Publicado: (2024)

Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models
por: Gu, Yanggan, et al.
Publicado: (2025)

Learning to Align Human Code Preferences
por: Yin, Xin, et al.
Publicado: (2025)

Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing
por: Tang, Yang, et al.
Publicado: (2025)

CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference
por: Dong, Zhitong, et al.
Publicado: (2026)

Aligning Crowd Feedback via Distributional Preference Reward Modeling
por: Li, Dexun, et al.
Publicado: (2024)

MTRec: Learning to Align with User Preferences via Mental Reward Models
por: Zhao, Mengchen, et al.
Publicado: (2025)

Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference
por: Shen, Xiangwei, et al.
Publicado: (2025)

ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignment
por: Wang, Hao, et al.
Publicado: (2026)

From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
por: Zhu, Mingkang, et al.
Publicado: (2025)

Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings
por: Li, Shiyu, et al.
Publicado: (2025)

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
por: Dong, Zibin, et al.
Publicado: (2023)

Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning
por: Li, Xuchen, et al.
Publicado: (2025)

Pragmatic Inference Chain (PIC) Improving LLMs' Reasoning of Authentic Implicit Toxic Language
por: Chen, Xi, et al.
Publicado: (2025)

Test-Time Deep Thinking to Explore Implicit Rules
por: Chen, Wentong, et al.
Publicado: (2026)

VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains
por: Li, Xuzhao, et al.
Publicado: (2025)

EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance
por: Yu, Song, et al.
Publicado: (2026)

SIPO: Stabilized and Improved Preference Optimization for Aligning Diffusion Models
por: Yang, Xiaomeng, et al.
Publicado: (2025)

MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning
por: Chen, Siyong, et al.
Publicado: (2025)

Adversarial Preference Learning for Robust LLM Alignment
por: Wang, Yuanfu, et al.
Publicado: (2025)

STEMVerse: A Dual-Axis Diagnostic Framework for STEM Reasoning in Large Language Models
por: Li, Xuzhao, et al.
Publicado: (2026)

Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization
por: Nguyen, Thanh Thi, et al.
Publicado: (2025)

Aligning Large Language Models with Searcher Preferences
por: Wu, Wei, et al.
Publicado: (2026)

CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging
por: Li, Zhenyu, et al.
Publicado: (2026)

RareAlert: Aligning heterogeneous large language model reasoning for early rare disease risk screening
por: Chen, Xi, et al.
Publicado: (2026)

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
por: Tian, Juanxi, et al.
Publicado: (2026)

SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning
por: Wu, Xiong Jun, et al.
Publicado: (2025)

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
por: Yang, Wen, et al.
Publicado: (2025)

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
por: Pu, Rui, et al.
Publicado: (2025)

Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation
por: Huang, Hongzhe, et al.
Publicado: (2024)

STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision
por: Li, Chen, et al.
Publicado: (2025)

Learning Transferable Latent User Preferences for Human-Aligned Decision Making
por: Hyk, Alina, et al.
Publicado: (2026)

Implicit Safety Alignment from Crowd Preferences
por: Lin, Qian, et al.
Publicado: (2026)

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

Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
por: Xu, Yuming, et al.
Publicado: (2026)

SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation
por: Zheng, Zaiyi, et al.
Publicado: (2026)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
por: Wen, Xumeng, et al.
Publicado: (2025)

Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback
por: Kim, Suzie, et al.
Publicado: (2025)