相关论文: Logic Against Bias: Textual Entailment Mitigates S…

We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in…

Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to…

The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy, polysemy) as well as abstract semantic notions (e.g., intensity). In this paper, we…

Societal bias towards certain communities is a big problem that affects a lot of machine learning systems. This work aims at addressing the racial bias present in many modern gender recognition systems. We learn race invariant…

Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

With the introduction of (large) language models, there has been significant concern about the unintended bias such models may inherit from their training data. A number of studies have shown that such models propagate gender stereotypes,…

This paper explores an empirical approach to learn more discriminantive sentence representations in an unsupervised fashion. Leveraging semantic graph smoothing, we enhance sentence embeddings obtained from pretrained models to improve…

Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on uncurated datasets scraped from the internet. The biases can be…

Detecting social bias in text is challenging due to nuance, subjectivity, and difficulty in obtaining good quality labeled datasets at scale, especially given the evolving nature of social biases and society. To address these challenges, we…

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

Considering the large amount of content created online by the minute, slang-aware automatic tools are critically needed to promote social good, and assist policymakers and moderators in restricting the spread of offensive language, abuse,…

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

The skip-thought model has been proven to be effective at learning sentence representations and capturing sentence semantics. In this paper, we propose a suite of techniques to trim and improve it. First, we validate a hypothesis that,…

Despite the huge progress in myriad generation tasks, pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts with maximization-based decoding algorithms for open-ended generation. We attribute their…

Pre-trained language models have proven their unique powers in capturing implicit language features. However, most pre-training approaches focus on the word-level training objective, while sentence-level objectives are rarely studied. In…

In this paper, we present a method for adversarial decomposition of text representation. This method can be used to decompose a representation of an input sentence into several independent vectors, each of them responsible for a specific…

Following the recent success of word embeddings, it has been argued that there is no such thing as an ideal representation for words, as different models tend to capture divergent and often mutually incompatible aspects like…

Pretrained multilingual models exhibit the same social bias as models processing English texts. This systematic review analyzes emerging research that extends bias evaluation and mitigation approaches into multilingual and non-English…