Related papers: Mitigating Social Biases in Language Models throug…

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…

Pretrained Language Models (PLMs) are widely used in NLP for various tasks. Recent studies have identified various biases that such models exhibit and have proposed methods to correct these biases. However, most of the works address a…

Large Language Models (LLMs) inherit societal biases from their training data, potentially leading to harmful or unfair outputs. While various techniques aim to mitigate these biases, their effects are often evaluated only along the…

As Natural Language Processing (NLP) and Machine Learning (ML) tools rise in popularity, it becomes increasingly vital to recognize the role they play in shaping societal biases and stereotypes. Although NLP models have shown success in…

Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an…

Large language models (LLMs) are trained on extensive text corpora, which inevitably include biased information. Although techniques such as Affective Alignment can mitigate some negative impacts of these biases, existing prompt-based…

Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking sensitive information, raising privacy concerns. In response,…

Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specifically designed for…

Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases, which may cause negative social impacts or even bring catastrophic results in application. Previous works on this problem…

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that…

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…

The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias…

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly. To improve language models in this regard, we propose to…

The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of their historical actions by implementing machine-learning techniques. These techniques facilitate the deletion of previously acquired knowledge…

Recent advancements in large language models (LLMs) have enabled their widespread use across diverse real-world applications. However, concerns remain about their tendency to encode and reproduce ideological biases along political and…

Large language models (LLMs) are known to inherit and even amplify societal biases present in their pre-training corpora, threatening fairness and social trust. To address this issue, recent work has explored ``editing'' LLM parameters to…

Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be…

Gender bias in vision-language models (VLMs) can reinforce harmful stereotypes and discrimination. In this paper, we focus on mitigating gender bias towards vision-language tasks. We identify object hallucination as the essence of gender…

Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots able to engage in conversations about visual inputs. However, their responses are influenced by societal biases present in their training…