Image de couverture de livre

The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Falahati, Ali, Amiri, Mohammad Mohammadi, Larson, Kate, Golab, Lukasz
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
par: Falahati, Ali, et autres
Publié: (2026)

Disentangled Structural and Featural Representation for Task-Agnostic Graph Valuation
par: Falahati, Ali, et autres
Publié: (2024)

A Median Perspective on Unlabeled Data for Out-of-Distribution Detection
par: Abbas, Momin, et autres
Publié: (2025)

SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching
par: Zhu, Yuxuan, et autres
Publié: (2025)

Toward Efficient Influence Function: Dropout as a Compression Tool
par: Zhang, Yuchen, et autres
Publié: (2025)

Jackpot! Alignment as a Maximal Lottery
par: Maura-Rivero, Roberto-Rafael, et autres
Publié: (2025)

Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes
par: Alipour, Mohammadsajad, et autres
Publié: (2025)

DriftXpress: Faster Drifting Models via Projected RKHS Fields
par: Falahati, Ali, et autres
Publié: (2026)

GASTON: Graph-Aware Social Transformer for Online Networks
par: Wloch, Olha, et autres
Publié: (2026)

When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop
par: Zhang, Yang, et autres
Publié: (2026)

Reward Shaping for Inference-Time Alignment: A Stackelberg Game Perspective
par: Wang, Haichuan, et autres
Publié: (2026)

Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
par: Wang, Fei, et autres
Publié: (2024)

Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs
par: Sel, Bilgehan, et autres
Publié: (2024)

Towards a Learning Theory of Representation Alignment
par: Insulla, Francesco, et autres
Publié: (2025)

Tokenized Bandit for LLM Decoding and Alignment
par: Shin, Suho, et autres
Publié: (2025)

Information as Structural Alignment: A Dynamical Theory of Continual Learning
par: Negulescu, Radu
Publié: (2026)

LLM Probability Concentration: How Alignment Shrinks the Generative Horizon
par: Yang, Chenghao, et autres
Publié: (2025)

OFMU: Optimization-Driven Framework for Machine Unlearning
par: Asif, Sadia, et autres
Publié: (2025)

Towards Reversible Model Merging For Low-rank Weights
par: Alipour, Mohammadsajad, et autres
Publié: (2025)

Manifold Approximation leads to Robust Kernel Alignment
par: Islam, Mohammad Tariqul, et autres
Publié: (2025)

SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
par: Sahoo, Subramanyam, et autres
Publié: (2026)

Direct Alignment with Heterogeneous Preferences
par: Shirali, Ali, et autres
Publié: (2025)

Learning Hyperspectral Images with Curated Text Prompts for Efficient Multimodal Alignment
par: Chatterjee, Abhiroop, et autres
Publié: (2025)

Pharmacist: Safety Alignment Data Curation for Large Language Models against Harmful Fine-tuning
par: Liu, Guozhi, et autres
Publié: (2025)

The Sign Estimator: LLM Alignment in the Face of Choice Heterogeneity
par: Aouad, Ali, et autres
Publié: (2025)

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
par: Asif, Sadia, et autres
Publié: (2026)

RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks
par: Yan, Mingxuan, et autres
Publié: (2025)

Liquid Ensemble Selection for Continual Learning
par: Blair, Carter, et autres
Publié: (2024)

Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
par: Zhou, Weichao, et autres
Publié: (2024)

Fair Dataset Distillation via Cross-Group Barycenter Alignment
par: Moslemi, Mohammad Hossein, et autres
Publié: (2026)

Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment
par: Gavenski, Nathan, et autres
Publié: (2026)

Liquid Democracy for Low-Cost Ensemble Pruning
par: Armstrong, Ben, et autres
Publié: (2024)

Model Alignment Search
par: Grant, Satchel
Publié: (2025)

ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned Alignment
par: Wanaskar, Kapil, et autres
Publié: (2026)

Any-Depth Alignment: Unlocking Innate Safety Alignment of LLMs to Any-Depth
par: Zhang, Jiawei, et autres
Publié: (2025)

Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment
par: Chen, Tiejin, et autres
Publié: (2026)

Automated Meta Prompt Engineering for Alignment with the Theory of Mind
par: Baughman, Aaron, et autres
Publié: (2025)

Space Alignment Matters: The Missing Piece for Inducing Neural Collapse in Long-Tailed Learning
par: Wang, Jinping, et autres
Publié: (2025)

Four Things People Should Know About Migraines
par: Parsa, Mohammad S., et autres
Publié: (2025)

Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients
par: Pourpanah, Farhad, et autres
Publié: (2024)