Related papers: Collapsed Language Models Promote Fairness

Collapsed Language Models Promote Fairness

URL: http://arxiv.org/abs/2410.04472v2
Date: Tue, 8 Oct 2024 13:03:49 GMT
Title: Collapsed Language Models Promote Fairness
Authors: Jingxuan Xu, Wuyang Chen, Linyi Li, Yao Zhao, Yunchao Wei,
Abstract summary: We find that debiased language models exhibit collapsed alignment between token representations and word embeddings. We design a principled fine-tuning method that can effectively improve fairness in a wide range of debiasing methods.
Score: 88.48232731113306
License: http://creativecommons.org/licenses/by/4.0/
Abstract: To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning, and more. Despite the development, it is nontrivial to reach a principled understanding of fairness and an effective algorithm that can consistently debias language models. In this work, by rigorous evaluations of Neural Collapse -- a learning phenomenon happen in last-layer representations and classifiers in deep networks -- on fairness-related words, we find that debiased language models exhibit collapsed alignment between token representations and word embeddings. More importantly, this observation inspires us to design a principled fine-tuning method that can effectively improve fairness in a wide range of debiasing methods, while still preserving the performance of language models on standard natural language understanding tasks. We attach our code at https://github.com/Xujxyang/Fairness-NC-main.

Related papers

Relation-based Counterfactual Data Augmentation and Contrastive Learning for Robustifying Natural Language Inference Models [0.0]
We propose a method in which we use token-based and sentence-based augmentation methods to generate counterfactual sentence pairs. We show that the proposed method can improve the performance and robustness of the NLI model.
arXiv Detail & Related papers (2024-10-28T03:43:25Z)
SpeechAlign: Aligning Speech Generation to Human Preferences [51.684183257809075]
We introduce SpeechAlign, an iterative self-improvement strategy that aligns speech language models to human preferences. We show that SpeechAlign can bridge the distribution gap and facilitate continuous self-improvement of the speech language model.
arXiv Detail & Related papers (2024-04-08T15:21:17Z)
Pixel Sentence Representation Learning [67.4775296225521]
In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
arXiv Detail & Related papers (2024-02-13T02:46:45Z)
Enhancing Context Through Contrast [0.4068270792140993]
We propose a novel Context Enhancement step to improve performance on neural machine translation. Unlike other approaches, we do not explicitly augment the data but view languages as implicit augmentations. Our method does not learn embeddings from scratch and can be generalised to any set of pre-trained embeddings.
arXiv Detail & Related papers (2024-01-06T22:13:51Z)
Commonsense Knowledge Transfer for Pre-trained Language Models [83.01121484432801]
We introduce commonsense knowledge transfer, a framework to transfer the commonsense knowledge stored in a neural commonsense knowledge model to a general-purpose pre-trained language model. It first exploits general texts to form queries for extracting commonsense knowledge from the neural commonsense knowledge model. It then refines the language model with two self-supervised objectives: commonsense mask infilling and commonsense relation prediction.
arXiv Detail & Related papers (2023-06-04T15:44:51Z)
Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Models [24.107358120517336]
In this work, we adopt a novel perspective wherein a pre-trained language model is itself simultaneously a policy, reward function, and transition function. An immediate consequence of this is that reward learning and language model fine-tuning can be performed jointly and directly, without requiring any further downstream policy optimization.
arXiv Detail & Related papers (2023-05-19T06:21:15Z)
Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
arXiv Detail & Related papers (2023-01-31T20:09:33Z)
SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
arXiv Detail & Related papers (2020-10-30T13:33:41Z)
CausaLM: Causal Model Explanation Through Counterfactual Language Models [33.29636213961804]
CausaLM is a framework for producing causal model explanations using counterfactual language representation models. We show that language representation models such as BERT can effectively learn a counterfactual representation for a given concept of interest. A byproduct of our method is a language representation model that is unaffected by the tested concept.
arXiv Detail & Related papers (2020-05-27T15:06:35Z)

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