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

Kong, Lingkai; Jiang, Haoming; Zhuang, Yuchen; Lyu, Jie; Zhao, Tuo; Zhang, Chao

doi:10.48550/arxiv.2010.11506

Cited by 3 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kong et al [25] encourage the model to output uniform distributions on pseudo off-manifold samples to alleviate the over-confidence in OOD regions. On the contrary, we apply off-manifold samples by enforcing the model to predict high vacuity:…”

Section: Utilizing Off-manifold Samplesmentioning

confidence: 99%

“…The embeddings of pre-trained transformers contain rich features that benefit the generated adversarial examples. Thus following [25], we evaluate off-manifold regularization on BERT [8].…”

Section: Utilizing Off-manifold Samplesmentioning

confidence: 99%

“…One partial explanation is over-parameterization [12]. Although transformers are pre-trained on a large corpus and get rich semantic information, it leads to overconfidence easily given limited labeled data during the fine-tuning stage [25]. Overall, compared to the Computer Vision (CV) domain, there is less work in qualifying uncertainty in the NLP domain.…”

mentioning

confidence: 99%

“…Thulasidasan et al [43] explore the improvement of calibration and predictive uncertainty of models trained with mix-up [49] in the NLP domain. Kong et al [25] use pseudo samples on and off the data manifold for calibration.…”

mentioning

confidence: 99%

“…However, generating adversarial examples via common gradient-based approaches is impossible in the NLP domain. Thus, we apply methods [11,25,41] to generate off-manifold adversarial examples from the embedding layer.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Uncertainty-Aware Reliable Text Classification

Khan

2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Deep neural networks have significantly contributed to the success in predictive accuracy for classification tasks. However, they tend to make over-confident predictions in real-world settings, where domain shifting and out-of-distribution (OOD) examples exist. Most research on uncertainty estimation focuses on computer vision because it provides visual validation on uncertainty quality. However, few have been presented in the natural language process domain. Unlike Bayesian methods that indirectly infer uncertainty through weight uncertainties, current evidential uncertainty-based methods explicitly model the uncertainty of class probabilities through subjective opinions. They further consider inherent uncertainty in data with different root causes, vacuity (i.e., uncertainty due to a lack of evidence) and dissonance (i.e., uncertainty due to conflicting evidence). In our paper, we firstly apply evidential uncertainty in OOD detection for text classification tasks. We propose an inexpensive framework that adopts both auxiliary outliers and pseudo off-manifold samples to train the model with prior knowledge of a certain class, which has high vacuity for OOD samples. Extensive empirical experiments demonstrate that our model based on evidential uncertainty outperforms other counterparts for detecting OOD examples. Our approach can be easily deployed to traditional recurrent neural networks and fine-tuned pre-trained transformers. CCS CONCEPTS• Computing methodologies → Natural language processing; Neural networks.

show abstract

Section: Utilizing Off-manifold Samplesmentioning

confidence: 99%

“…The embeddings of pre-trained transformers contain rich features that benefit the generated adversarial examples. Thus following [25], we evaluate off-manifold regularization on BERT [8].…”

Section: Utilizing Off-manifold Samplesmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Uncertainty-Aware Reliable Text Classification

Khan

2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach

Zuo¹,

Chen²,

Jiang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Adversarial training has been shown to improve the generalization performance of deep learning models in various natural language processing tasks. Existing works usually formulate adversarial training as a zero-sum game, which is solved by alternating gradient descent/ascent algorithms. Such a formulation treats the adversarial and the defending players equally, which is undesirable because only the defending player contributes to the generalization performance. To address this issue, we propose Stackelberg Adversarial Training (SALT), which formulates adversarial training as a Stackelberg game. This formulation induces a competition between a leader and a follower, where the follower generates perturbations, and the leader trains the model subject to the perturbations. Different from conventional adversarial training, in SALT, the leader is in an advantageous position. When the leader moves, it recognizes the strategy of the follower and takes the anticipated follower's outcomes into consideration. Such a leader's advantage enables us to improve the model fitting to the unperturbed data. The leader's strategic information is captured by the Stackelberg gradient, which is obtained using an unrolling algorithm. Our experimental results on a set of machine translation and natural language understanding tasks show that SALT outperforms existing adversarial training baselines across all tasks.

show abstract

Learning ULMFiT and Self-Distillation with Calibration for Medical Dialogue System

Ao,

Acharya

2021

Preprint

View full text Add to dashboard Cite

A medical dialogue system is essential for healthcare service as providing primary clinical advice and diagnoses. It has been gradually adopted and practiced in medical organizations in the form of a conversational bot, largely due to the advancement of NLP. In recent years, the introduction of state-of-theart deep learning models and transfer learning techniques like Universal Language Model Fine Tuning (ULMFiT) and Knowledge Distillation (KD) largely contributes to the performance of NLP tasks. However, some deep neural networks are poorly calibrated and wrongly estimate the uncertainty. Hence the model is not trustworthy, especially in sensitive medical decision-making systems and safety tasks. In this paper, we investigate the well-calibrated model for ULMFiT and self-distillation (SD) in a medical dialogue system. The calibrated ULMFiT (CULMFiT) is obtained by incorporating label smoothing (LS), a commonly used regularization technique to achieve a wellcalibrated model. Moreover, we apply the technique to recalibrate the confidence score called temperature scaling (TS) with KD to observe its correlation with network calibration. To further understand the relation between SD and calibration, we use both fixed and optimal temperatures to fine-tune the whole model. All experiments are conducted on the consultation backpain dataset collected by experts then further validated using a large publicly medial dialogue corpus. We empirically show that our proposed methodologies outperform conventional methods in terms of accuracy and robustness.

show abstract

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

Cited by 3 publications

References 24 publications

Uncertainty-Aware Reliable Text Classification

Uncertainty-Aware Reliable Text Classification

Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach

Learning ULMFiT and Self-Distillation with Calibration for Medical Dialogue System

Contact Info

Product

Resources

About