Uncertainty Aware Learning for Language Model Alignment
- URL: http://arxiv.org/abs/2406.04854v1
- Date: Fri, 7 Jun 2024 11:37:45 GMT
- Title: Uncertainty Aware Learning for Language Model Alignment
- Authors: Yikun Wang, Rui Zheng, Liang Ding, Qi Zhang, Dahua Lin, Dacheng Tao,
- Abstract summary: We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios.
We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples.
Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
- Score: 97.36361196793929
- License: http://creativecommons.org/publicdomain/zero/1.0/
- Abstract: 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).
Related papers
- Feasible Learning [78.6167929413604]
We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample.
Our empirical analysis, spanning image classification, age regression, and preference optimization in large language models, demonstrates that models trained via FL can learn from data while displaying improved tail behavior compared to ERM, with only a marginal impact on average performance.
arXiv Detail & Related papers (2025-01-24T20:39:38Z) - SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples [54.760757107700755]
Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance.
The class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation.
We propose a method that enhances the performance of Imbalanced Semi-Supervised Learning by Mining Hard Examples (SeMi)
arXiv Detail & Related papers (2025-01-10T14:35:16Z) - Realistic Test-Time Adaptation of Vision-Language Models [23.972884634610413]
Vision-Language Models (VLMs) have been widely leveraged to improve predictive performance.
Previous works on transductive or test-time adaptation (TTA) often make strong assumptions about the data distribution.
Our work challenges these favorable deployment scenarios, and introduces a more realistic evaluation framework.
arXiv Detail & Related papers (2025-01-07T12:17:25Z) - LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training [2.762397703396293]
Loss Prediction Loss with Gradient Norm (LPLgrad) is designed to quantify model uncertainty effectively and improve the accuracy of image classification tasks.
LPLgrad operates in two distinct phases: (i) em Training Phase aims to predict the loss for input features by jointly training a main model and an auxiliary model.
This dual-model approach enhances the ability to extract complex input features and learn intrinsic patterns from the data effectively.
arXiv Detail & Related papers (2024-11-20T18:12:59Z) - Quantifying Prediction Consistency Under Model Multiplicity in Tabular LLMs [10.494477811252034]
Fine-tuning large language models can lead to textitfine-tuning multiplicity, where equally well-performing models make conflicting predictions on the same inputs.
This raises critical concerns about the robustness and reliability of Tabular LLMs.
This work proposes a novel metric to quantify the robustness of individual predictions without expensive model retraining.
arXiv Detail & Related papers (2024-07-04T22:22:09Z) - Take the Bull by the Horns: Hard Sample-Reweighted Continual Training
Improves LLM Generalization [165.98557106089777]
A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data.
Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets.
We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
arXiv Detail & Related papers (2024-02-22T04:10:57Z) - Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised
Language Understanding [38.11411155621616]
We study self-training as one of the predominant semi-supervised learning approaches.
We present UPET, a novel Uncertainty-aware self-Training framework.
We show that UPET achieves a substantial improvement in terms of performance and efficiency.
arXiv Detail & Related papers (2023-10-19T02:18:29Z) - Learning Objective-Specific Active Learning Strategies with Attentive
Neural Processes [72.75421975804132]
Learning Active Learning (LAL) suggests to learn the active learning strategy itself, allowing it to adapt to the given setting.
We propose a novel LAL method for classification that exploits symmetry and independence properties of the active learning problem.
Our approach is based on learning from a myopic oracle, which gives our model the ability to adapt to non-standard objectives.
arXiv Detail & Related papers (2023-09-11T14:16:37Z) - Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples.
We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries.
We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
arXiv Detail & Related papers (2020-02-27T10:22:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.