# Uncertainty Aware Learning for Language Model Alignment

arXiv: https://arxiv.org/abs/2406.04854 · HTML: https://mlsanity.com/paper/2406.04854/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 24 of its 36 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 24 of 24)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Predictive Uncertainty Estimation via Prior Networks](https://mlsanity.com/paper/1802.10501/) (2018)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning](https://mlsanity.com/paper/2312.15685/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT](https://mlsanity.com/paper/2302.10198/) (2023)
- [A Tutorial on Principal Component Analysis](https://mlsanity.com/paper/1404.1100/) (2014)
- [Towards Making the Most of ChatGPT for Machine Translation](https://mlsanity.com/paper/2303.13780/) (2023)
- [Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models](https://mlsanity.com/paper/2303.13809/) (2023)
- [Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism](https://mlsanity.com/paper/2305.18438/) (2023)
- [Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks](https://mlsanity.com/paper/2310.13800/) (2023)
- [Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicity](https://mlsanity.com/paper/2203.11572/) (2022)
- [Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction](https://mlsanity.com/paper/2403.09963/) (2024)
- [Self-Evolution Learning for Discriminative Language Model Pretraining](https://mlsanity.com/paper/2305.15275/) (2023)

## Built on by (most cited first, 13 of 13)

- [TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning](https://mlsanity.com/paper/2509.25760/) (2025)
- [CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models](https://mlsanity.com/paper/2407.02408/) (2024)
- [Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges](https://mlsanity.com/paper/2507.19672/) (2025)
- [GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation](https://mlsanity.com/paper/2502.05911/) (2025)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)
- [mathbbUSCD: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding](https://mlsanity.com/paper/2409.05923/) (2024)
- [Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models](https://mlsanity.com/paper/2506.07575/) (2025)
- [Self-Filtered Distillation with LLMs-generated Trust Indicators for Reliable Patent Classification](https://mlsanity.com/paper/2510.05431/) (2025)
- [Conformal Feedback Alignment: Quantifying Answer-Level Reliability for Robust LLM Alignment](https://mlsanity.com/paper/2601.17329/) (2026)
- [UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers](https://mlsanity.com/paper/2602.02952/) (2026)
- [Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning](https://mlsanity.com/paper/2511.18859/) (2025)
- [Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era](https://mlsanity.com/paper/2605.18903/) (2026)
- [Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs](https://mlsanity.com/paper/2607.12273/) (2026)

## Abstract (arXiv)

As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook the intrinsic uncertainty of tasks, learning all data samples equally. This may lead to suboptimal data efficiency and model performance. In response, we propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios, by introducing the sample uncertainty (elicited from more capable LLMs). We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Analysis shows that our UAL indeed facilitates better token clustering in the feature space, validating our hypothesis. Extensive experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning. Notably, LLMs aligned in a mixed scenario have achieved an average improvement of 10.62% on high-entropy tasks (i.e., AlpacaEval leaderboard), and 1.81% on complex low-entropy tasks (i.e., MetaMath and GSM8K).