# Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

arXiv: https://arxiv.org/abs/2010.11506 · HTML: https://mlsanity.com/paper/2010.11506/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 17 of 17)

- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification](https://mlsanity.com/paper/2108.02035/) (2021)
- [Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis](https://mlsanity.com/paper/2210.04714/) (2022)
- [A Close Look into the Calibration of Pre-trained Language Models](https://mlsanity.com/paper/2211.00151/) (2022)
- [Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data](https://mlsanity.com/paper/2106.08977/) (2021)
- [Multi-task Active Learning for Pre-trained Transformer-based Models](https://mlsanity.com/paper/2208.05379/) (2022)
- [RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models](https://mlsanity.com/paper/2309.06619/) (2023)
- [DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling](https://mlsanity.com/paper/2305.19395/) (2023)
- [A Data Cartography based MixUp for Pre-trained Language Models](https://mlsanity.com/paper/2205.03403/) (2022)
- [Thrust: Adaptively Propels Large Language Models with External Knowledge](https://mlsanity.com/paper/2307.10442/) (2023)
- [Program-Aided Reasoners (better) Know What They Know](https://mlsanity.com/paper/2311.09553/) (2023)
- [Explaining Predictive Uncertainty by Looking Back at Model Explanations](https://mlsanity.com/paper/2201.03742/) (2022)
- [Learning ULMFiT and Self-Distillation with Calibration for Medical Dialogue System](https://mlsanity.com/paper/2107.09625/) (2021)
- [Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation](https://mlsanity.com/paper/2108.01812/) (2021)
- [An Interdisciplinary Perspective on Evaluation and Experimental Design for Visual Text Analytics: Position Paper](https://mlsanity.com/paper/2209.11534/) (2022)
- [Extracting Victim Counts from Text](https://mlsanity.com/paper/2302.12367/) (2023)

## Abstract (arXiv)

Fine-tuned pre-trained language models can suffer from severe miscalibration for both in-distribution and out-of-distribution (OOD) data due to over-parameterization. To mitigate this issue, we propose a regularized fine-tuning method. Our method introduces two types of regularization for better calibration: (1) On-manifold regularization, which generates pseudo on-manifold samples through interpolation within the data manifold. Augmented training with these pseudo samples imposes a smoothness regularization to improve in-distribution calibration. (2) Off-manifold regularization, which encourages the model to output uniform distributions for pseudo off-manifold samples to address the over-confidence issue for OOD data. Our experiments demonstrate that the proposed method outperforms existing calibration methods for text classification in terms of expectation calibration error, misclassification detection, and OOD detection on six datasets. Our code can be found at https://github.com/Lingkai-Kong/Calibrated-BERT-Fine-Tuning.