Cover Image

The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Liu, Mingyi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
by: Zhang, Xinnan, et al.
Published: (2025)

Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting
by: Dai, Hui, et al.
Published: (2026)

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment
by: Wang, Haowen, et al.
Published: (2025)

Sample-Efficient Alignment for LLMs
by: Liu, Zichen, et al.
Published: (2024)

On Evaluating LLM Alignment by Evaluating LLMs as Judges
by: Liu, Yixin, et al.
Published: (2025)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
by: Liu, Xiao, et al.
Published: (2023)

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
by: Bu, Yuyan, et al.
Published: (2026)

BOND: Aligning LLMs with Best-of-N Distillation
by: Sessa, Pier Giuseppe, et al.
Published: (2024)

Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
by: Liang, Kaiqu, et al.
Published: (2024)

Aligners: Decoupling LLMs and Alignment
by: Ngweta, Lilian, et al.
Published: (2024)

Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
by: Xu, Wanghan, et al.
Published: (2025)

H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs
by: Tekin, Selim Furkan, et al.
Published: (2024)

Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
by: Achintalwar, Swapnaja, et al.
Published: (2024)

The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
by: Aakanksha, et al.
Published: (2024)

FormalAlign: Automated Alignment Evaluation for Autoformalization
by: Lu, Jianqiao, et al.
Published: (2024)

LLMs Should Express Uncertainty Explicitly
by: Guo, Junyu, et al.
Published: (2026)

Do LLMs Recognize Your Latent Preferences? A Benchmark for Latent Information Discovery in Personalized Interaction
by: Tsaknakis, Ioannis, et al.
Published: (2025)

Towards Scalable Automated Alignment of LLMs: A Survey
by: Cao, Boxi, et al.
Published: (2024)

Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
by: Kang, Yipeng, et al.
Published: (2024)

AlignDistil: Token-Level Language Model Alignment as Adaptive Policy Distillation
by: Zhang, Songming, et al.
Published: (2025)

Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits
by: Patel, Dev, et al.
Published: (2025)

Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge
by: Liu, Genglin, et al.
Published: (2023)

HAL: Inducing Human-likeness in LLMs with Alignment
by: Hasan, Masum, et al.
Published: (2026)

SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
by: Liu, Liangxin, et al.
Published: (2024)

True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning
by: Tan, Weihao, et al.
Published: (2024)

Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios
by: Dang, Yunkai, et al.
Published: (2024)

A Comprehensive Evaluation framework of Alignment Techniques for LLMs
by: Azmat, Muneeza, et al.
Published: (2025)

LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
by: Li, Junsong, et al.
Published: (2025)

Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
by: Lyu, Kaifeng, et al.
Published: (2024)

Evaluating the Relevance of Uncertainty Estimators for LLM Hallucination
by: Agnimo, Yedidia, et al.
Published: (2026)

Estimation of Concept Explanations Should be Uncertainty Aware
by: Piratla, Vihari, et al.
Published: (2023)

Efficient Preference-based Reinforcement Learning via Aligned Experience Estimation
by: Bai, Fengshuo, et al.
Published: (2024)

Enabling Weak LLMs to Judge Response Reliability via Meta Ranking
by: Liu, Zijun, et al.
Published: (2024)

Universal Response and Emergence of Induction in LLMs
by: Luick, Niclas
Published: (2024)

We're Different, We're the Same: Creative Homogeneity Across LLMs
by: Wenger, Emily, et al.
Published: (2025)

Nudging: Inference-time Alignment of LLMs via Guided Decoding
by: Fei, Yu, et al.
Published: (2024)

Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
by: Miyamoto, Sora, et al.
Published: (2026)

How Uncertainty Estimation Scales with Sampling in Reasoning Models
by: Del, Maksym, et al.
Published: (2026)

Token Homogenization under Positional Bias
by: Yusupov, Viacheslav, et al.
Published: (2025)

Revisiting Uncertainty Estimation and Calibration of Large Language Models
by: Tao, Linwei, et al.
Published: (2025)