Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists

• URL: http://arxiv.org/abs/2203.09192v1
• Date: Thu, 17 Mar 2022 09:29:50 GMT
• Title: Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
• Abstract summary: We propose a knowledge-free Entropy-based Attention Regularization (EAR) to discourage overfitting to training-specific terms. EAR reveals overfitting terms, i.e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.
• Score: 32.01761060664898
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms like gay, or women, resulting in false positives, severe unintended bias, and lower performance. Most mitigation techniques use lists of identity terms or samples from the target domain during training. However, this approach requires a-priori knowledge and introduces further bias if important terms are neglected. Instead, we propose a knowledge-free Entropy-based Attention Regularization (EAR) to discourage overfitting to training-specific terms. An additional objective function penalizes tokens with low self-attention entropy. We fine-tune BERT via EAR: the resulting model matches or exceeds state-of-the-art performance for hate speech classification and bias metrics on three benchmark corpora in English and Italian. EAR also reveals overfitting terms, i.e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.

Related papers

• Neutral-Reference Prompting for Vision-Language Models [14.563492336625004]
  We propose NeRP, a plug-and-play prompting correction strategy that improves discrimination on unseen classes without modifying model parameters.<n>We show that NeRP substantially improves accuracy on unseen classes while preserving known-class prediction performance.
  arXiv  Detail & Related papers  (2026-05-15T04:54:08Z)
• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• When Priors Backfire: On the Vulnerability of Unlearnable Examples to Pretraining [28.704214093822472]
  Unlearnable Examples (UEs) serve as a data protection strategy that generates imperceptible perturbations to mislead models into learning spurious correlations instead of underlying semantics.<n>In this paper, we uncover a fundamental vulnerability of UEs that emerges when learning starts from a pretrained model.<n>We propose BAIT (Binding Artificial perturbations to Incorrect Targets), a novel bi-level optimization formulation.
  arXiv  Detail & Related papers  (2026-03-05T02:10:40Z)
• Making Bias Non-Predictive: Training Robust LLM Judges via Reinforcement Learning [91.8584139564909]
  Large language models (LLMs) increasingly serve as automated judges, yet they remain susceptible to cognitive biases.<n>We propose Epistemic Independence Training (EIT), a reinforcement learning framework grounded in a key principle.<n>EIT operationalizes this through a balanced conflict strategy where bias signals are equally likely to support correct and incorrect answers.
  arXiv  Detail & Related papers  (2026-02-02T01:43:48Z)
• ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models [26.544938760265136]
  Deep learning models inadvertently learn spurious correlations between targets and non-essential features.<n>In this paper, we propose a novel post hoc spurious bias mitigation framework without requiring group labels.<n>Our framework, termed ShortcutProbe, identifies prediction shortcuts that reflect potential non-robustness in predictions in a given model's latent space.
  arXiv  Detail & Related papers  (2025-05-20T04:21:17Z)
• DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models [50.54264918467997]
  Pre-trained language models (PLMs) have achieved impressive results on various natural language processing tasks. Recent research has revealed that these models often rely on superficial features and shortcuts instead of developing a genuine understanding of language. We propose Divergence Based Regularization (DBR) to mitigate this shortcut learning behavior.
  arXiv  Detail & Related papers  (2025-02-25T16:44:10Z)
• ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition [52.537021302246664]
  Action recognition models often suffer from background bias (i.e., inferring actions based on background cues) and foreground bias (i.e., relying on subject appearance) We propose ALBAR, a novel adversarial training method that mitigates foreground and background biases without requiring specialized knowledge of the bias attributes. We evaluate our method on established background and foreground bias protocols, setting a new state-of-the-art and strongly improving combined debiasing performance by over 12% absolute on HMDB51.
  arXiv  Detail & Related papers  (2025-01-31T20:47:06Z)
• Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization [13.773597081543185]
  We introduce a novel debiasing regularization technique based on the class-wise variance of embeddings. Our method does not require attribute labels and targets any attribute, thus addressing the shortcomings of existing debiasing methods.
  arXiv  Detail & Related papers  (2024-09-29T03:56:50Z)
• Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness [10.081447621656523]
  The impact on language modeling ability can be alleviated given a high-quality and long-contextualized debiasing corpus. The effectiveness of task-agnostic debiasing hinges on the quantitative bias level of both the task-specific data used for downstream applications and the debiased model. We propose a novel framework which can Propagate Socially-fair Debiasing to Downstream Fine-tuning, ProSocialTuning.
  arXiv  Detail & Related papers  (2024-06-06T15:11:11Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• Causality and Independence Enhancement for Biased Node Classification [56.38828085943763]
  We propose a novel Causality and Independence Enhancement (CIE) framework, applicable to various graph neural networks (GNNs) Our approach estimates causal and spurious features at the node representation level and mitigates the influence of spurious correlations. Our approach CIE not only significantly enhances the performance of GNNs but outperforms state-of-the-art debiased node classification methods.
  arXiv  Detail & Related papers  (2023-10-14T13:56:24Z)
• Self-supervised debiasing using low rank regularization [59.84695042540525]
  Spurious correlations can cause strong biases in deep neural networks, impairing generalization ability. We propose a self-supervised debiasing framework potentially compatible with unlabeled samples. Remarkably, the proposed debiasing framework significantly improves the generalization performance of self-supervised learning baselines.
  arXiv  Detail & Related papers  (2022-10-11T08:26:19Z)
• Power of Explanations: Towards automatic debiasing in hate speech detection [19.26084350822197]
  Hate speech detection is a common downstream application of natural language processing (NLP) in the real world. We propose an automatic misuse detector (MiD) relying on an explanation method for detecting potential bias.
  arXiv  Detail & Related papers  (2022-09-07T14:14:03Z)
• Causal Disentanglement for Semantics-Aware Intent Learning in Recommendation [30.85573846018658]
  We propose an unbiased and semantics-aware disentanglement learning called CaDSI. CaDSI explicitly models the causal relations underlying recommendation task. It produces semantics-aware representations via disentangling users true intents aware of specific item context.
  arXiv  Detail & Related papers  (2022-02-05T15:17:03Z)
• Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
  We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap. We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
  arXiv  Detail & Related papers  (2021-09-09T10:10:29Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Understanding and Mitigating Annotation Bias in Facial Expression Recognition [3.325054486984015]
  Most existing works assume that human-generated annotations can be considered gold-standard and unbiased. We focus on facial expression recognition and compare the label biases between lab-controlled and in-the-wild datasets. We propose an AU-Calibrated Facial Expression Recognition framework that utilizes facial action units (AUs) and incorporates the triplet loss into the objective function.
  arXiv  Detail & Related papers  (2021-08-19T05:28:07Z)
• Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures [62.562760228942054]
  Existing approaches to improve robustness against dataset biases mostly focus on changing the training objective. We propose to augment the input sentences in the training data with their corresponding predicate-argument structures. We show that without targeting a specific bias, our sentence augmentation improves the robustness of transformer models against multiple biases.
  arXiv  Detail & Related papers  (2020-10-23T16:22:05Z)

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.