Copertina

Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Takahashi, Hiroshi, Iwata, Tomoharu, Kumagai, Atsutoshi, Kanai, Sekitoshi, Yamada, Masanori, Nishida, Kosuke, Shinoda, Kazutoshi
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Debiasing Reward Models via Causally Motivated Inference-Time Intervention
di: Shinoda, Kazutoshi, et al.
Pubblicazione: (2026)

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
di: Takahashi, Hiroshi, et al.
Pubblicazione: (2024)

Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
di: Takahashi, Hiroshi, et al.
Pubblicazione: (2025)

Transfer Learning with Pre-trained Conditional Generative Models
di: Yamaguchi, Shin'ya, et al.
Pubblicazione: (2022)

Meta-learning for Positive-unlabeled Classification
di: Kumagai, Atsutoshi, et al.
Pubblicazione: (2024)

Test-Time Alignment of LLMs via Sampling-Based Optimal Control in pre-logit space
di: Kanai, Sekitoshi, et al.
Pubblicazione: (2025)

Let's Put Ourselves in Sally's Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Models
di: Shinoda, Kazutoshi, et al.
Pubblicazione: (2025)

Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods
di: Ito, Akira, et al.
Pubblicazione: (2024)

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets
di: Yamashita, Tomoya, et al.
Pubblicazione: (2025)

Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
di: Ito, Akira, et al.
Pubblicazione: (2025)

ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind
di: Shinoda, Kazutoshi, et al.
Pubblicazione: (2025)

Meta-learning Representations for Learning from Multiple Annotators
di: Kumagai, Atsutoshi, et al.
Pubblicazione: (2025)

Post-pre-training for Modality Alignment in Vision-Language Foundation Models
di: Yamaguchi, Shin'ya, et al.
Pubblicazione: (2025)

Test-time Adaptation for Regression by Subspace Alignment
di: Adachi, Kazuki, et al.
Pubblicazione: (2024)

Direct Density Ratio Optimization: A Statistically Consistent Approach to Aligning Large Language Models
di: Higuchi, Rei, et al.
Pubblicazione: (2025)

Covariance-aware Feature Alignment with Pre-computed Source Statistics for Test-time Adaptation to Multiple Image Corruptions
di: Adachi, Kazuki, et al.
Pubblicazione: (2022)

Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes
di: Nishida, Kosuke, et al.
Pubblicazione: (2024)

Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
di: Yamaguchi, Shin'ya, et al.
Pubblicazione: (2024)

Data-driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems
di: Iwata, Tomoharu, et al.
Pubblicazione: (2025)

Can LLMs Detect Their Own Hallucinations?
di: Kadotani, Sora, et al.
Pubblicazione: (2025)

Evaluating Time-Series Training Dataset through Lens of Spectrum in Deep State Space Models
di: Kanai, Sekitoshi, et al.
Pubblicazione: (2024)

Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals
di: Gerard, Patrick, et al.
Pubblicazione: (2026)

Pretraining and Updates of Domain-Specific LLM: A Case Study in the Japanese Business Domain
di: Takahashi, Kosuke, et al.
Pubblicazione: (2024)

VAL-Bench: Belief Consistency as a measure for Value Alignment in Language Models
di: Gupta, Aman, et al.
Pubblicazione: (2025)

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching
di: Nguyen, Truong, et al.
Pubblicazione: (2026)

Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
di: Wang, Jialu, et al.
Pubblicazione: (2026)

Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models
di: Kim, Jongho, et al.
Pubblicazione: (2025)

Out-of-the-Box Conditional Text Embeddings from Large Language Models
di: Yamada, Kosuke, et al.
Pubblicazione: (2025)

TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment
di: Nguyen, Thi-Nhung, et al.
Pubblicazione: (2026)

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
di: Li, Yiwei, et al.
Pubblicazione: (2025)

Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search
di: Cao, Zhiyu, et al.
Pubblicazione: (2026)

MoCoRP: Modeling Consistent Relations between Persona and Response for Persona-based Dialogue
di: Lee, Kyungro, et al.
Pubblicazione: (2025)

Preference Optimization by Estimating the Ratio of the Data Distribution
di: Kim, Yeongmin, et al.
Pubblicazione: (2025)

Preference Ranking Optimization for Human Alignment
di: Song, Feifan, et al.
Pubblicazione: (2023)

OptiHive: Ensemble Selection for LLM-Based Optimization via Statistical Modeling
di: Bouscary, Maxime, et al.
Pubblicazione: (2025)

Self-Consistency Preference Optimization
di: Prasad, Archiki, et al.
Pubblicazione: (2024)

Binary Classifier Optimization for Large Language Model Alignment
di: Jung, Seungjae, et al.
Pubblicazione: (2024)

Accelerated Preference Optimization for Large Language Model Alignment
di: He, Jiafan, et al.
Pubblicazione: (2024)

Self-Play Preference Optimization for Language Model Alignment
di: Wu, Yue, et al.
Pubblicazione: (2024)

Stepwise Alignment for Constrained Language Model Policy Optimization
di: Wachi, Akifumi, et al.
Pubblicazione: (2024)