Image de couverture de livre

Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Amin, Adil
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Growing Pains of Frontier Models: When Leaderboards Stop Separating and What to Measure Next
par: Amin, Adil
Publié: (2026)

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
par: Frank, Gregory N.
Publié: (2026)

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
par: Luo, Haozheng, et autres
Publié: (2026)

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples
par: Gao, Chengqian, et autres
Publié: (2025)

Layer by Layer: Uncovering Hidden Representations in Language Models
par: Skean, Oscar, et autres
Publié: (2025)

Phase Transitions in the Output Distribution of Large Language Models
par: Arnold, Julian, et autres
Publié: (2024)

Explaining Large Language Models with gSMILE
par: Dehghani, Zeinab, et autres
Publié: (2025)

MENTIS: What Belief Changes Under Alignment? Measuring Multi-Scale Latent Torsion in Language Models
par: Saha, Partha Pratim, et autres
Publié: (2026)

The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models
par: Flamant, Cedric, et autres
Publié: (2026)

On the Robustness of Reward Models for Language Model Alignment
par: Hong, Jiwoo, et autres
Publié: (2025)

Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models
par: Wong, Wai Tuck, et autres
Publié: (2026)

Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
par: Messina, Alberto, et autres
Publié: (2026)

Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models
par: Sun, Shaoning, et autres
Publié: (2026)

Hidden State Poisoning Attacks against Mamba-based Language Models
par: Mercier, Alexandre Le, et autres
Publié: (2026)

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
par: Ghandeharioun, Asma, et autres
Publié: (2024)

Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
par: Rafailov, Rafael, et autres
Publié: (2024)

Pareto Multi-Objective Alignment for Language Models
par: He, Qiang, et autres
Publié: (2025)

Evolutionary Contrastive Distillation for Language Model Alignment
par: Katz-Samuels, Julian, et autres
Publié: (2024)

VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
par: Shetty, Anudeex, et autres
Publié: (2025)

Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation
par: Baumann, Joachim, et autres
Publié: (2025)

Binary Classifier Optimization for Large Language Model Alignment
par: Jung, Seungjae, et autres
Publié: (2024)

Accelerated Preference Optimization for Large Language Model Alignment
par: He, Jiafan, et autres
Publié: (2024)

Self-Play Preference Optimization for Language Model Alignment
par: Wu, Yue, et autres
Publié: (2024)

Probabilistic Token Alignment for Large Language Model Fusion
par: Zeng, Runjia, et autres
Publié: (2025)

Stepwise Alignment for Constrained Language Model Policy Optimization
par: Wachi, Akifumi, et autres
Publié: (2024)

Rethinking the Role of Proxy Rewards in Language Model Alignment
par: Kim, Sungdong, et autres
Publié: (2024)

Value Augmented Sampling for Language Model Alignment and Personalization
par: Han, Seungwook, et autres
Publié: (2024)

Spectral Editing of Activations for Large Language Model Alignment
par: Qiu, Yifu, et autres
Publié: (2024)

Reviving The Classics: Active Reward Modeling in Large Language Model Alignment
par: Shen, Yunyi, et autres
Publié: (2025)

Training Language Models with Language Feedback at Scale
par: Scheurer, Jérémy, et autres
Publié: (2023)

Scaling Embeddings Outperforms Scaling Experts in Language Models
par: Liu, Hong, et autres
Publié: (2026)

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
par: Ye, Tian, et autres
Publié: (2024)

(Im)possibility of Automated Hallucination Detection in Large Language Models
par: Karbasi, Amin, et autres
Publié: (2025)

Entropy Aware Reward Guidance for Diffusion Language Model Alignment
par: Tejaswi, Atula, et autres
Publié: (2026)

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
par: Liu, Qin, et autres
Publié: (2024)

Atlas-Alignment: Making Interpretability Transferable Across Language Models
par: Puri, Bruno, et autres
Publié: (2025)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
par: Liu, Xiao, et autres
Publié: (2023)

Multilingual Instruction Tuning With Just a Pinch of Multilinguality
par: Shaham, Uri, et autres
Publié: (2024)

Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment
par: Zhang, Yifan, et autres
Publié: (2024)

Scaling Inference-Efficient Language Models
par: Bian, Song, et autres
Publié: (2025)