Models for natural language understanding (NLU) tasks often rely on the idiosyncratic biases of the dataset, which make them brittle against test cases outside the training distribution. Recently, several proposed debiasing methods are shown to be very effective in improving out-of-distribution performance. However, their improvements come at the expense of performance drop when models are evaluated on the in-distribution data, which contain examples with higher diversity. This seemingly inevitable trade-off may not tell us much about the changes in the reasoning and understanding capabilities of the resulting models on broader types of examples beyond the small subset represented in the out-of-distribution data. In this paper, we address this trade-off by introducing a novel debiasing method, called confidence regularization, which discourage models from exploiting biases while enabling them to receive enough incentive to learn from all the training examples. We evaluate our method on three NLU tasks and show that, in contrast to its predecessors, it improves the performance on out-of-distribution datasets (e.g., 7pp gain on HANS dataset) while maintaining the original in-distribution accuracy.
Existing Natural Language Understanding (NLU) models have been shown to incorporate dataset biases leading to strong performance on in-distribution (ID) test sets but poor performance on out-of-distribution (OOD) ones. We introduce a simple yet effective debiasing framework whereby the shallow representations of the main model are used to derive a bias model and both models are trained simultaneously. We demonstrate on three well studied NLU tasks that despite its simplicity, our method leads to competitive OOD results. It significantly outperforms other debiasing approaches on two tasks, whil…
The University of Tokyo（东京大学）；National Institute of Informatics（国立信息学研究所）
Debiasing language models from unwanted behaviors in Natural Language Understanding tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and avoid uncovering more advanced and desirable linguistic features. A multitude of effective debiasing approaches has been proposed, but flexibility remains a major issue. For the most part, models must be retrained to find a new set of weights with debiased behavior. We propose a new debiasing method in which we identify debiased pruning masks that can be app…
Technische Universität Darmstadt（达姆施塔特工业大学）；Ubiquitous Knowledge Processing Lab (UKP-TUDA)（普适知识处理实验室（UKP-TUDA））；Research Training Group AIPHES（AIPHES研究培训小组）
NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. Recently proposed debiasing methods are shown to be effective in mitigating this tendency. However, these methods rely on a major assumption that the types of bias should be known a-priori, which limits their application to many NLU tasks and datasets. In this work, we present the first step to bridge this gap by introducing a self-debiasing framework that prevents models from mainly utilizing biases without knowing them in advance. The proposed framework is general and com…
Technion – Israel Institute of Technology（以色列理工学院）
Model robustness to bias is often determined by the generalization on carefully designed out-of-distribution datasets. Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring models into making unbiased predictions. An underlying assumption behind such methods is that this also leads to the discovery of more robust features in the model's inner representations. We propose a general probing-based framework that allows for post-hoc interpretation of biases in language models, and use an information-theoretic approach to measure the extr…
Shandong University（山东大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；University of Amsterdam（阿姆斯特丹大学）；Baidu Inc.（百度公司）
Natural language understanding (NLU) models often rely on dataset biases rather than intended task-relevant features to achieve high performance on specific datasets. As a result, these models perform poorly on datasets outside the training distribution. Some recent studies address this issue by reducing the weights of biased samples during the training process. However, these methods still encode biased latent features in representations and neglect the dynamic nature of bias, which hinders model prediction. We propose an NLU debiasing method, named debiasing contrastive learning (DCT), to si…
A Heuristic Perspective on Debiasing Language Models
Inner Mongolia University（内蒙古大学）；Xiamen University（厦门大学）；University of Sydney（悉尼大学）；Nanjing University of Science and Technology（南京理工大学）；Harbin Institute of Technology（哈尔滨工业大学）；Zhejiang University（浙江大学）
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an empirical survey of five recently proposed bias mitigation techniques: Counterfactual Data Augmentation (CDA), Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebias. We quantify the effectiveness of each technique using three intrinsic bias benchmarks while also measuring the impact of these techniques on a model's language modeling ability, as w…
Datasets with significant proportions of bias present threats for training a trustworthy model on NLU tasks. Despite yielding great progress, current debiasing methods impose excessive reliance on the knowledge of bias attributes. Definition of the attributes, however, is elusive and varies across different datasets. Furthermore, leveraging these attributes at input level to bias mitigation may leave a gap between intrinsic properties and the underlying decision rule. To narrow down this gap and liberate the supervision on bias, we suggest extending bias mitigation into feature space. Therefor…
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；RIKEN Center for Computational Science（理化学研究所计算科学中心）；Tokyo Institute of Technology（东京工业大学）；Center for Social Data Science, University of Copenhagen（哥本哈根大学社会数据科学中心）
Much of recent progress in NLU was shown to be due to models' learning dataset-specific heuristics. We conduct a case study of generalization in NLI (from MNLI to the adversarially constructed HANS dataset) in a range of BERT-based architectures (adapters, Siamese Transformers, HEX debiasing), as well as with subsampling the data and increasing the model size. We report 2 successful and 3 unsuccessful strategies, all providing insights into how Transformer-based models learn to generalize.
UGID: Unified Graph Isomorphism for Debiasing Large Language Models
University of Electronic Science and Technology of China（电子科技大学）；Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed人工智能大学）；South China University of Technology（华南理工大学）
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
Laboratory for Artificial Intelligence in Mathematics Education, Stevens Institute of Technology（数学教育中的人工智能实验室，史蒂文斯理工学院）；Independent Researcher（独立研究者）；NLP2CT Lab, Department of Computer and Information Science, University of Macau（NLP2CT实验室，澳门大学计算机与信息科学系）
Fudan University（复旦大学）；KTH Royal Institute of Technology（KTH皇家理工学院）；Nanyang Technological University（南洋理工大学）
Natural language understanding (NLU) models tend to rely on spurious correlations (i.e., dataset bias) to achieve high performance on in-distribution datasets but poor performance on out-of-distribution ones. Most of the existing debiasing methods often identify and weaken these samples with biased features (i.e., superficial surface features that cause such spurious correlations). However, down-weighting these samples obstructs the model in learning from the non-biased parts of these samples. To tackle this challenge, in this paper, we propose to eliminate spurious correlations in a fine-grai…
EPFL（洛桑联邦理工学院）；Idiap Research Institute（伊迪亚普研究所）；Harvard University（哈佛大学）；Massachusetts Institute of Technology（麻省理工学院）
Several recent studies have shown that strong natural language understanding (NLU) models are prone to relying on unwanted dataset biases without learning the underlying task, resulting in models that fail to generalize to out-of-domain datasets and are likely to perform poorly in real-world scenarios. We propose two learning strategies to train neural models, which are more robust to such biases and transfer better to out-of-domain datasets. The biases are specified in terms of one or more bias-only models, which learn to leverage the dataset biases. During training, the bias-only models' pre…
