Related papers: Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models

Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models

URL: http://arxiv.org/abs/2110.07736v1
Date: Thu, 14 Oct 2021 21:40:03 GMT
Title: Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models
Authors: Tianlu Wang, Diyi Yang, Xuezhi Wang
Abstract summary: Many problems can be attributed to models exploiting spurious correlations, or shortcuts between the training data and the task labels. In this paper, we aim to automatically identify such spurious correlations in NLP models at scale. We show that our proposed method can effectively and efficiently identify a scalable set of "shortcuts", and mitigating these leads to more robust models in multiple applications.
Score: 19.21465581259624
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Abstract: Recently, NLP models have achieved remarkable progress across a variety of tasks; however, they have also been criticized for being not robust. Many robustness problems can be attributed to models exploiting spurious correlations, or shortcuts between the training data and the task labels. Models may fail to generalize to out-of-distribution data or be vulnerable to adversarial attacks if spurious correlations are exploited through the training process. In this paper, we aim to automatically identify such spurious correlations in NLP models at scale. We first leverage existing interpretability methods to extract tokens that significantly affect model's decision process from the input text. We then distinguish "genuine" tokens and "spurious" tokens by analyzing model predictions across multiple corpora and further verify them through knowledge-aware perturbations. We show that our proposed method can effectively and efficiently identify a scalable set of "shortcuts", and mitigating these leads to more robust models in multiple applications.

Related papers

DISCO: DISCovering Overfittings as Causal Rules for Text Classification Models [6.369258625916601]
Post-hoc interpretability methods fail to capture the models' decision-making process fully. Our paper introduces DISCO, a novel method for discovering global, rule-based explanations. DISCO supports interactive explanations, enabling human inspectors to distinguish spurious causes in the rule-based output.
arXiv Detail & Related papers (2024-11-07T12:12:44Z)
Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles [95.49699178874683]
We propose DiffDiv, an ensemble diversification framework exploiting Diffusion Probabilistic Models (DPMs) We show that DPMs can generate images with novel feature combinations, even when trained on samples displaying correlated input features. We show that DPM-guided diversification is sufficient to remove dependence on shortcut cues, without a need for additional supervised signals.
arXiv Detail & Related papers (2023-11-23T15:47:33Z)
Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks [92.32670915472099]
We propose an ensemble diversification framework exploiting the generation of synthetic counterfactuals using Diffusion Probabilistic Models (DPMs) We show that diffusion-guided diversification can lead models to avert attention from shortcut cues, achieving ensemble diversity performance comparable to previous methods requiring additional data collection.
arXiv Detail & Related papers (2023-10-03T17:37:52Z)
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
arXiv Detail & Related papers (2023-03-24T16:03:21Z)
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates [26.527311287924995]
influence tuning can help deconfounding the model from spurious patterns in data. We show that in a controlled setup, influence tuning can help deconfounding the model from spurious patterns in data.
arXiv Detail & Related papers (2021-10-07T06:59:46Z)
Explaining and Improving Model Behavior with k Nearest Neighbor Representations [107.24850861390196]
We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions. We show that kNN representations are effective at uncovering learned spurious associations. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
arXiv Detail & Related papers (2020-10-18T16:55:25Z)
Learning Diverse Representations for Fast Adaptation to Distribution Shift [78.83747601814669]
We present a method for learning multiple models, incorporating an objective that pressures each to learn a distinct way to solve the task. We demonstrate our framework's ability to facilitate rapid adaptation to distribution shift.
arXiv Detail & Related papers (2020-06-12T12:23:50Z)
AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
arXiv Detail & Related papers (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.