相关论文: Socially Aware Bias Measurements for Hindi Languag…

Pretrained language models inherently exhibit various social biases, prompting a crucial examination of their social impact across various linguistic contexts due to their widespread usage. Previous studies have provided numerous methods…

In multilingual societies like the Indian subcontinent, use of code-switched languages is much popular and convenient for the users. In this paper, we study offense and abuse detection in the code-switched pair of Hindi and English (i.e.…

Modern models for common NLP tasks often employ machine learning techniques and train on journalistic, social media, or other culturally-derived text. These have recently been scrutinized for racial and gender biases, rooting from inherent…

Languages usually switch within a multilingual speech signal, especially in a bilingual society. This phenomenon is referred to as code-switching (CS), making automatic speech recognition (ASR) challenging under a multilingual scenario. We…

It is a well-known fact that current AI-based language technology -- language models, machine translation systems, multilingual dictionaries and corpora -- focuses on the world's 2-3% most widely spoken languages. Recent research efforts…

Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to…

The term "Code Mixed" refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount of adaptation as time goes on. It is critical to detect…

Transformer-based pretrained large language models (PLM) such as BERT and GPT have achieved remarkable success in NLP tasks. However, PLMs are prone to encoding stereotypical biases. Although a burgeoning literature has emerged on…

Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social…

The analysis of data in which multiple languages are represented has gained popularity among computational linguists in recent years. So far, much of this research focuses mainly on the improvement of computational methods and largely…

Large Language Models(LLMs) have revolutionized various applications in natural language processing (NLP) by providing unprecedented text generation, translation, and comprehension capabilities. However, their widespread deployment has…

Language models based on the Transformer architecture have achieved state-of-the-art performance on a wide range of NLP tasks such as text classification, question-answering, and token classification. However, this performance is usually…

The growing deployment of large language models (LLMs) across diverse cultural contexts necessitates a deeper understanding of LLMs' representations of different cultures. Prior work has focused on evaluating the cultural awareness of LLMs…

We propose a bias-aware methodology to engage with power relations in natural language processing (NLP) research. NLP research rarely engages with bias in social contexts, limiting its ability to mitigate bias. While researchers have…

Studies in bias and fairness in natural language processing have primarily examined social biases within a single language and/or across few attributes (e.g. gender, race). However, biases can manifest differently across various languages…

The rise of concern around Natural Language Processing (NLP) technologies containing and perpetuating social biases has led to a rich and rapidly growing area of research. Gender bias is one of the central biases being analyzed, but to date…

Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social…

Sycophancy, the tendency of language models to prioritize agreement with user preferences over principled reasoning, has been identified as a persistent alignment failure in English-language evaluations. However, it remains unclear whether…

We know from prior work that LLMs encode social biases, and that this manifests in clinical tasks. In this work we adopt tools from mechanistic interpretability to unveil sociodemographic representations and biases within LLMs in the…

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…