| Challenge: | Despite impressive performance on many text classification tasks, deep neural networks tend to learn frequent superficial patterns that are specific to the training data and do not always generalize well. |
| Approach: | They propose a method that represents latent topical confounds and a model which “unlearns” confounding features by predicting both the label of the input text and the confound. |
| Outcome: | The proposed model generalizes better and learns features indicative of the writing style rather than the content. |
Similar Papers
How to Generalize the Detection of AI-Generated Text: Confounding Neurons (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Linguistic and domain confounders introduce spurious correlations, leading to poor out-of-distribution (OOD) performance. |
| Approach: | They propose a novel post-hoc, neuron-level intervention framework to disentangle AI-generated text detection factors from data-specific biases. |
| Outcome: | The proposed framework reduces topic-specific biases by encoding individual neurons within transformers-based detectors rather than task-specific signals. |
Text Classification with Few Examples using Controlled Generalization (N19-1)
Copied to clipboard
| Challenge: | Current training data for text classification is limited, resulting in limited generalization capacity. |
| Approach: | They propose a feed-forward network that can generalize from unlabeled parsed corpora to produce task-specific semantic vectors. |
| Outcome: | The proposed approach is especially effective in low-data scenarios compared to state-of-the-art methods. |
Are Text Classifiers Xenophobic? A Country-Oriented Bias Detection Method with Least Confounding Variables (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for detecting biases are biased because of confounding variables . authors propose a method to detect the biased classifier on any type of unlabeled data . |
| Approach: | They propose a method to detect biases of a specific fine-tuned classifier on unlabeled data. |
| Outcome: | The proposed method detects biases on unlabeled data on named entity perturbations . it uses name-entity recognition on target-domain data and morphosynctactically different languages spoken in relation to countries of the target groups . |
Do Neural Language Models Overcome Reporting Bias? (2020.coling-main)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained language models can overcome reporting bias by estimating the plausibility of rare but unspoken facts. |
| Approach: | They revisit the experiments conducted by Gordon and Van Durme (2013) . they find that pre-trained language models overestimate the very rare . |
| Outcome: | The proposed approach overestimates the rare at the expense of the rare, while minimizing reporting bias. |
Predicting Reference: What do Language Models Learn about Discourse Models? (2020.emnlp-main)
Copied to clipboard
| Challenge: | a growing literature that probes neural language models to assess their latent acquisition of grammatical knowledge has not investigated their acquisition of discourse modeling ability. |
| Approach: | They draw on a psycholinguistic literature that has established how different contexts affect referential biases concerning who is likely to be referred to next. |
| Outcome: | The proposed models do not resemble human language users, the authors show . their models capture the linguistic knowledge required to perform discourse modeling . |
FIND: Human-in-the-Loop Debugging Deep Text Classifiers (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models are limited in the number of available datasets and lack the necessary tools to improve them. |
| Approach: | They propose a framework which enables humans to debug deep learning text classifiers by disabling irrelevant hidden features. |
| Outcome: | Experiments show that using FIND, humans can improve CNN text classifiers trained on different types of imperfect datasets. |
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings (2025.coling-main)
Copied to clipboard
| Challenge: | Existing work in this field has looked most commonly into gender bias, racial bias, and religious bias. |
| Approach: | They propose an algorithm that uses a neural network to perform ‘soft debiasing’ and build on the seminal work of (CITATION) and (CitATION). |
| Outcome: | The proposed algorithm outperforms current methods on gender, race, and religion metrics on a wide range of metrics. |
Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for text classification using autoregressive language models are limited . authors propose a novel technique for text classification using autoreregressives . |
| Approach: | They propose a two-step technique for text classification using autoregressive language models . they use a set of perplexity and log-likelihood based numeric features to elicit a text instance . |
| Outcome: | The proposed technique eliminates parameter updates in LMs and does not limit training examples . it is evaluated across 5 datasets and compares with multiple competent baselines . |
It’s Morphin’ Time! Combating Linguistic Discrimination with Inflectional Perturbations (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work on societal bias in NLP focuses on race and gender . linguistic background is a unique attribute that has been largely ignored in the field . |
| Approach: | They examine linguistic background to craft plausible adversarial examples that expose biases in popular NLP models. |
| Outcome: | The proposed model improves robustness without sacrificing performance on clean data. |
Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for classification are overly confident on unseen examples . despite recent advances in NLP, some categories of distribution shift still pose serious challenges. |
| Approach: | They propose a method that generates OOD examples representative of novel classes and trains to decrease confidence on them. |
| Outcome: | The proposed method improves classifiers' ability to detect and abstain on novel class examples over previous methods by 2.3% and 5.5% over previous approaches. |