Image de couverture de livre

Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Henneking, Carl-Leander, Beger, Claas
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus
par: Beger, Claas, et autres
Publié: (2025)

CoCoNUT: Structural Code Understanding does not fall out of a tree
par: Beger, Claas, et autres
Publié: (2025)

$π$-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering
par: Wan, Chao, et autres
Publié: (2025)

Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models
par: Agnihotri, Akhil, et autres
Publié: (2025)

Data-Centric Human Preference with Rationales for Direct Preference Alignment
par: Just, Hoang Anh, et autres
Publié: (2024)

Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment
par: Lin, Zhiyu, et autres
Publié: (2025)

Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment
par: Hou, Xiaoyang, et autres
Publié: (2026)

Distortion of AI Alignment: Does Preference Optimization Optimize for Preferences?
par: Gölz, Paul, et autres
Publié: (2025)

Preference Learning for AI Alignment: a Causal Perspective
par: Kobalczyk, Katarzyna, et autres
Publié: (2025)

Align-then-Unlearn: Embedding Alignment for LLM Unlearning
par: Spohn, Philipp, et autres
Publié: (2025)

Alignment-Aware Decoding
par: Berdoz, Frédéric, et autres
Publié: (2025)

From Demonstrations to Rewards: Alignment Without Explicit Human Preferences
par: Zeng, Siliang, et autres
Publié: (2025)

Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization
par: Park, Ryan, et autres
Publié: (2024)

Decoding Musical Origins: Distinguishing Human and AI Composers
par: Tsai, Cheng-Yang, et autres
Publié: (2025)

Preference Alignment with Flow Matching
par: Kim, Minu, et autres
Publié: (2024)

Generalized Preference Optimization: A Unified Approach to Offline Alignment
par: Tang, Yunhao, et autres
Publié: (2024)

Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners
par: Ng, Wen Zheng Terence, et autres
Publié: (2025)

Human Alignment of Large Language Models through Online Preference Optimisation
par: Calandriello, Daniele, et autres
Publié: (2024)

Beyond Preferences: Learning Alignment Principles Grounded in Human Reasons and Values
par: Bell, Henry, et autres
Publié: (2026)

A Probabilistic Approach for Model Alignment with Human Comparisons
par: Cao, Junyu, et autres
Publié: (2024)

MaxMin-RLHF: Alignment with Diverse Human Preferences
par: Chakraborty, Souradip, et autres
Publié: (2024)

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters
par: Xiao, Teng, et autres
Publié: (2025)

Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale
par: Bell, Henry, et autres
Publié: (2026)

ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference
par: Cai, Tianchi, et autres
Publié: (2023)

Exploring Human-AI Conceptual Alignment through the Prism of Chess
par: Lomasov, Semyon, et autres
Publié: (2025)

AI-Guided Human-In-the-Loop Inverse Design of High Performance Engineering Structures
par: Ha, Dat Quoc, et autres
Publié: (2026)

The Illusion of Fit: Spatially Resolved Assessment of Constitutive Model Validity in Elastography and Physics-Based Inverse Problems
par: Scholz, Vincent C., et autres
Publié: (2025)

Less is More: Improving LLM Alignment via Preference Data Selection
par: Deng, Xun, et autres
Publié: (2025)

Bayesian Cosmic Void Finding with Graph Flows
par: Thiele, Leander
Publié: (2026)

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

Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference
par: Gao, Mingqi, et autres
Publié: (2024)

Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
par: Cousins, Cyrus, et autres
Publié: (2025)

Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network
par: Kinoshita, Yuri, et autres
Publié: (2023)

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
par: Zhang, Yuheng, et autres
Publié: (2025)

Can Revealed Preferences Clarify LLM Alignment and Steering?
par: Yamin, Khurram, et autres
Publié: (2026)

Distributional Preference Alignment of LLMs via Optimal Transport
par: Melnyk, Igor, et autres
Publié: (2024)

A TextGCN-Based Decoding Approach for Improving Remote Sensing Image Captioning
par: Das, Swadhin, et autres
Publié: (2024)

Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
par: Bahng, Hyojin, et autres
Publié: (2025)

Incorporating Human Flexibility through Reward Preferences in Human-AI Teaming
par: Bhambri, Siddhant, et autres
Publié: (2023)

Decoding-Time Language Model Alignment with Multiple Objectives
par: Shi, Ruizhe, et autres
Publié: (2024)