相关论文: Can Small-Scale Data Poisoning Exacerbate Dialect-…

Style features such as friendly, helpful, or concise are widely used in prompts to steer the behavior of Large Language Model (LLM) conversational agents, yet their unintended side effects remain poorly understood. In this work, we present…

Uses of pejorative expressions can be benign or actively empowering. When models for abuse detection misclassify these expressions as derogatory, they inadvertently censor productive conversations held by marginalized groups. One way to…

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data,…

Large language models (LLMs) have become integral to our professional workflows and daily lives. Nevertheless, these machine companions of ours have a critical flaw: the huge amount of data which endows them with vast and diverse knowledge,…

Data contamination -- the accidental consumption of evaluation examples within the pre-training data -- can undermine the validity of evaluation benchmarks. In this paper, we present a rigorous analysis of the effects of contamination on…

With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased significantly. One of these security risks is the threat of…

Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models. We conduct this study on three dimensions: training…

Large language models produce human-like text that drive a growing number of applications. However, recent literature and, increasingly, real world observations, have demonstrated that these models can generate language that is toxic,…

In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite being widely applied, in-context learning is vulnerable to…

Recently efforts have been made by social media platforms as well as researchers to detect hateful or toxic language using large language models. However, none of these works aim to use explanation, additional context and victim community…

It's been said that "Language Models are Unsupervised Multitask Learners." Indeed, self-supervised language models trained on "positive" examples of English text generalize in desirable ways to many natural language tasks. But if such…

Multilingual studies of social bias in open-ended LLM generation remain limited: most existing benchmarks are English-centric, template-based, or restricted to recognizing pre-specified stereotypes. We introduce StereoTales, a multilingual…

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such…

Despite the remarkable performance of foundation vision-language models, the shared representation space for text and vision can also encode harmful label associations detrimental to fairness. While prior work has uncovered bias in…

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…

Language models (LMs) must be both safe and equitable to be responsibly deployed in practice. With safety in mind, numerous detoxification techniques (e.g., Dathathri et al. 2020; Krause et al. 2020) have been proposed to mitigate toxic LM…

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Neural approaches to ranking based on pre-trained language models are highly effective in ad-hoc search. However, the computational expense of these models can limit their application. As such, a process known as knowledge distillation is…

Training-data poisoning attacks can induce targeted, undetectable failure in deep neural networks by corrupting a vanishingly small fraction of training labels. We demonstrate this on acoustic vehicle classification using the MELAUDIS urban…

Causal learning is the cognitive process of developing the capability of making causal inferences based on available information, often guided by normative principles. This process is prone to errors and biases, such as the illusion of…