Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models

• URL: http://arxiv.org/abs/2305.19249v1
• Date: Tue, 30 May 2023 17:35:31 GMT
• Title: Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
• Authors: Guande He, Jianfei Chen, Jun Zhu
• Abstract summary: Large pre-trained language models (PLMs) have demonstrated strong performance on natural language understanding (NLU) tasks through fine-tuning. However, fine-tuned models still suffer from overconfident predictions, especially in out-of-domain settings. We demonstrate that the PLMs are well-calibrated on the masked language modeling task with robust predictive confidence under domain shift. We show that preserving pre-trained features can improve the calibration of fine-tuned language models.
• Score: 23.881825575095945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large pre-trained language models (PLMs) have demonstrated strong performance on natural language understanding (NLU) tasks through fine-tuning. However, fine-tuned models still suffer from overconfident predictions, especially in out-of-domain settings. In this paper, we tackle the problem of calibrating fine-tuned language models. We demonstrate that the PLMs are well-calibrated on the masked language modeling task with robust predictive confidence under domain shift, yet the fine-tuned models fail to retain such property due to catastrophic forgetting, which impacts the calibration on the downstream classification task. In light of these observations, we evaluate the calibration of several methods that preserve pre-trained features and show that preserving pre-trained features can improve the calibration of fine-tuned language models. Among these methods, our proposed method that encourages the fine-tuned model to learn generative representations with auxiliary language modeling objective achieves competitive accuracy and the lowest expected calibration error compared to several strong baselines under both in-domain and out-of-domain settings on three downstream NLU tasks.

Related papers

• Observational Scaling Laws and the Predictability of Language Model Performance [51.2336010244645]
  We propose an observational approach that bypasses model training and instead builds scaling laws from 100 publically available models. We show that several emergent phenomena follow a smooth, sigmoidal behavior and are predictable from small models. We show how to predict the impact of post-training interventions like Chain-of-Thought and Self-Consistency as language model capabilities continue to improve.
  arXiv  Detail & Related papers  (2024-05-17T17:49:44Z)
• On the Calibration of Large Language Models and Alignment [63.605099174744865]
  Confidence calibration serves as a crucial tool for gauging the reliability of deep models. We conduct a systematic examination of the calibration of aligned language models throughout the entire construction process. Our work sheds light on whether popular LLMs are well-calibrated and how the training process influences model calibration.
  arXiv  Detail & Related papers  (2023-11-22T08:57:55Z)
• CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration [59.48235003469116]
  We show that data augmentation consistently enhances OOD performance. We also show that CF augmented models which are easier to calibrate also exhibit much lower entropy when assigning importance.
  arXiv  Detail & Related papers  (2023-09-14T16:16:40Z)
• Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models [37.39843935632105]
  We propose an approach to adapt the prior class distribution to perform text classification tasks without the need for labelled samples. Results show that these methods outperform the un-adapted model for different number of training shots in the prompt.
  arXiv  Detail & Related papers  (2023-07-13T12:11:36Z)
• On the Calibration of Massively Multilingual Language Models [15.373725507698591]
  Massively Multilingual Language Models (MMLMs) have recently gained popularity due to their surprising effectiveness in cross-lingual transfer. We first investigate the calibration of MMLMs in the zero-shot setting and observe a clear case of miscalibration in low-resource languages. We also find that few-shot examples in the language can further help reduce the calibration errors, often substantially.
  arXiv  Detail & Related papers  (2022-10-21T21:41:56Z)
• Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization [94.4409074435894]
  We propose a novel and effective fine-tuning framework, named Layerwise Noise Stability Regularization (LNSR) Specifically, we propose to inject the standard Gaussian noise and regularize hidden representations of the fine-tuned model. We demonstrate the advantages of the proposed method over other state-of-the-art algorithms including L2-SP, Mixout and SMART.
  arXiv  Detail & Related papers  (2022-06-12T04:42:49Z)
• On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency [47.90235939359225]
  We propose a novel mixup strategy for pre-trained language models that improves model calibration further. Our method achieves the lowest expected calibration error compared to strong baselines on both in-domain and out-of-domain test samples.
  arXiv  Detail & Related papers  (2022-03-14T23:45:08Z)
• Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning [74.25168207651376]
  Fine-tuning pre-trained language models to downstream cross-lingual tasks has shown promising results. We leverage continual learning to preserve the cross-lingual ability of the pre-trained model when we fine-tune it to downstream tasks. Our methods achieve better performance than other fine-tuning baselines on the zero-shot cross-lingual part-of-speech tagging and named entity recognition tasks.
  arXiv  Detail & Related papers  (2020-04-29T14:07:18Z)
• Calibrating Structured Output Predictors for Natural Language Processing [8.361023354729731]
  We propose a general calibration scheme for output entities of interest in neural-network based structured prediction models. Our proposed method can be used with any binary class calibration scheme and a neural network model. We show that our method outperforms current calibration techniques for named-entity-recognition, part-of-speech and question answering.
  arXiv  Detail & Related papers  (2020-04-09T04:14:46Z)
• CALM: Continuous Adaptive Learning for Language Modeling [18.72860206714457]
  Training large language representation models has become a standard in the natural language processing community. We demonstrate that in practice these pre-trained models present performance deterioration in the form of catastrophic forgetting. We propose CALM, Continuous Adaptive Learning for Language Modeling: techniques to render models which retain knowledge across multiple domains.
  arXiv  Detail & Related papers  (2020-04-08T03:51:17Z)
• Calibration of Pre-trained Transformers [55.57083429195445]
  We focus on BERT and RoBERTa in this work, and analyze their calibration across three tasks: natural language inference, paraphrase detection, and commonsense reasoning. We show that: (1) when used out-of-the-box, pre-trained models are calibrated in-domain, and compared to baselines, their calibration error out-of-domain can be as much as 3.5x lower; (2) temperature scaling is effective at further reducing calibration error in-domain, and using label smoothing to deliberately increase empirical uncertainty helps calibrate posteriors out-of-domain.
  arXiv  Detail & Related papers  (2020-03-17T18:58:44Z)

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.