Copertina

Shared Nature, Unique Nurture: PRISM for Pluralistic Reasoning via In-context Structure Modeling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tu, Guancheng, Zhang, Shiyang, Zhang, Tianyu, Zhang, Yi, Yang, Diji
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Many Minds from One Model: Bayesian-Inspired Transformers for Population Diversity
di: Yang, Diji, et al.
Pubblicazione: (2025)

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks
di: Lo, Chung-Hsiang, et al.
Pubblicazione: (2026)

Beyond Introspection: Reinforcing Thinking via Externalist Behavioral Feedback
di: Yang, Diji, et al.
Pubblicazione: (2024)

Exploring Chain-of-Thought Reasoning for Steerable Pluralistic Alignment
di: Zhang, Yunfan, et al.
Pubblicazione: (2025)

PluralLLM: Pluralistic Alignment in LLMs via Federated Learning
di: Srewa, Mahmoud, et al.
Pubblicazione: (2025)

Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
di: Guo, Hanze, et al.
Pubblicazione: (2025)

PRISM: Structured Optimization via Anisotropic Spectral Shaping
di: Yang, Yujie
Pubblicazione: (2026)

Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding
di: Zhang, Yunkai, et al.
Pubblicazione: (2025)

APPA: Adaptive Preference Pluralistic Alignment for Fair Federated RLHF of LLMs
di: Srewa, Mahmoud, et al.
Pubblicazione: (2026)

PRISM: Parallel Residual Iterative Sequence Model
di: Jiang, Jie, et al.
Pubblicazione: (2026)

PRISM-FCP: Byzantine-Resilient Federated Conformal Prediction via Partial Sharing
di: Lari, Ehsan, et al.
Pubblicazione: (2026)

PRISM: Gauge-Invariant Tangent-Space Differentially Private LoRA
di: Wang, Shihao, et al.
Pubblicazione: (2026)

Retrieval-Augmented Robots via Retrieve-Reason-Act
di: Temiraliev, Izat, et al.
Pubblicazione: (2026)

PRISM: Distributed Inference for Foundation Models at Edge
di: Qazi, Muhammad Azlan, et al.
Pubblicazione: (2025)

Rethinking Parameter Sharing as Graph Coloring for Structured Compression
di: Zhang, Boyang, et al.
Pubblicazione: (2025)

PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences
di: Chen, Daiwei, et al.
Pubblicazione: (2024)

PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
di: Zhao, Wanjia, et al.
Pubblicazione: (2025)

Learning Permutation Distributions via Reflected Diffusion on Ranks
di: He, Sizhuang, et al.
Pubblicazione: (2026)

Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models
di: Qiu, Yifu, et al.
Pubblicazione: (2025)

PRISM: Differentially Private Synthetic Data with Structure-Aware Budget Allocation for Prediction
di: Asiaee, Amir, et al.
Pubblicazione: (2026)

Federated Graph Semantic and Structural Learning
di: Huang, Wenke, et al.
Pubblicazione: (2024)

Personalized PCA: Decoupling Shared and Unique Features
di: Shi, Naichen, et al.
Pubblicazione: (2022)

Online high-precision prediction method for injection molding product weight by integrating time series/non-time series mixed features and feature attention mechanism
di: Li, Maoyuan, et al.
Pubblicazione: (2025)

Hierarchical Structure Sharing Empowers Multi-task Heterogeneous GNNs for Customer Expansion
di: Feng, Xinyue, et al.
Pubblicazione: (2024)

Multi-Strategy Improved Snake Optimizer Accelerated CNN-LSTM-Attention-Adaboost for Trajectory Prediction
di: Li, Shiyang
Pubblicazione: (2025)

Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
di: Cheng, Ziheng, et al.
Pubblicazione: (2025)

Pairwise Calibrated Rewards for Pluralistic Alignment
di: Halpern, Daniel, et al.
Pubblicazione: (2025)

Pluralistic Alignment Over Time
di: Klassen, Toryn Q., et al.
Pubblicazione: (2024)

PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation
di: Fang, Dengzhao, et al.
Pubblicazione: (2026)

MixDPO: Modeling Preference Strength for Pluralistic Alignment
di: Imai, Saki, et al.
Pubblicazione: (2026)

VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
di: Zheng, Shenyan, et al.
Pubblicazione: (2026)

PRISM: Fast Online LLM Serving via Scheduling-Memory Co-design
di: Qu, Xingyu, et al.
Pubblicazione: (2026)

Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy
di: Freedman, Rachel
Pubblicazione: (2026)

PRISM: PRIor from corpus Statistics for topic Modeling
di: Ishon, Tal, et al.
Pubblicazione: (2026)

Multi-agent In-context Coordination via Decentralized Memory Retrieval
di: Jiang, Tao, et al.
Pubblicazione: (2025)

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
di: Zhao, Yang, et al.
Pubblicazione: (2026)

PRISM: Demystifying Retention and Interaction in Mid-Training
di: Runwal, Bharat, et al.
Pubblicazione: (2026)

SOFA-FL: Self-Organizing Hierarchical Federated Learning with Adaptive Clustered Data Sharing
di: Ni, Yi, et al.
Pubblicazione: (2025)

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
di: Chiu, Yu Ying, et al.
Pubblicazione: (2025)

CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models
di: Tu, Ruibo, et al.
Pubblicazione: (2024)