Related papers: Reducing Sentiment Bias in Language Models via Cou…

Biases induced to text by generative models have become an increasingly large topic in recent years. In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analysis models. For this,…

Many text corpora exhibit socially problematic biases, which can be propagated or amplified in the models trained on such data. For example, doctor cooccurs more frequently with male pronouns than female pronouns. In this study we (i)…

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes.…

Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have…

Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and…

Approaches for mitigating bias in supervised models are designed to reduce models' dependence on specific sensitive features of the input data, e.g., mentioned social groups. However, in the case of hate speech detection, it is not always…

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…

This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual demographic subgroups. We focus on weight and activation quantization strategies and examine their…

Bias mitigation approaches reduce models' dependence on sensitive features of data, such as social group tokens (SGTs), resulting in equal predictions across the sensitive features. In hate speech detection, however, equalizing model…

As language models become increasingly integrated into our digital lives, Personalized Text Generation (PTG) has emerged as a pivotal component with a wide range of applications. However, the bias inherent in user written text, often used…

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

The presence of specific linguistic signals particular to a certain sub-group can become highly salient to language models during training. In automated decision-making settings, this may lead to biased outcomes when models rely on cues…

Sentiment analysis (SA) systems are used in many products and hundreds of languages. Gender and racial biases are well-studied in English SA systems, but understudied in other languages, with few resources for such studies. To remedy this,…

Target-oriented multimodal sentiment classification seeks to predict sentiment polarity for specific targets from image-text pairs. While existing works achieve competitive performance, they often over-rely on textual content and fail to…

Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and…

The rapid advancement of large language models (LLMs) and their growing integration into daily life underscore the importance of evaluating and ensuring their fairness. In this work, we examine fairness within the domain of emotional theory…

Recent advances in machine learning have led to computer systems that are human-like in behaviour. Sentiment analysis, the automatic determination of emotions in text, is allowing us to capitalize on substantial previously unattainable…

Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class. The generated counterfactuals provide insight into the reasoning behind a model's…

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more…

The rise of large language models (LLMs) has revolutionized natural language processing (NLP), yet the influence of prompt sentiment, a latent affective characteristic of input text, remains underexplored. This study systematically examines…