Related papers: Mitigating harm in language models with conditiona…

The age of social media is flooded with Internet memes, necessitating a clear grasp and effective identification of harmful ones. This task presents a significant challenge due to the implicit meaning embedded in memes, which is not…

Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified…

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…

Large language models (LLMs), trained on large-scale text, have recently attracted significant attention for their strong performance across many tasks. Motivated by this, we investigate whether a text-trained LLM can help localize fake…

With the rise of online hate speech, automatic detection of Hate Speech, Offensive texts as a natural language processing task is getting popular. However, very little research has been done to detect unintended social bias from these toxic…

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during…

Pretraining datasets are foundational to the development of multimodal models, yet they often have inherent biases and toxic content from the web-scale corpora they are sourced from. In this paper, we investigate the prevalence of toxicity…

A human decision-maker benefits the most from an AI assistant that corrects for their biases. For problems such as generating interpretation of a radiology report given findings, a system predicting only highly likely outcomes may be less…

Automatic hate speech detection is hampered by the scarcity of labeled datasetd, leading to poor generalization. We employ pretrained language models (LMs) to alleviate this data bottleneck. We utilize the GPT LM for generating large…

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

Text classification is crucial for applications such as sentiment analysis and toxic text filtering, but it still faces challenges due to the complexity and ambiguity of natural language. Recent advancements in deep learning, particularly…

In today's digital world, social media plays a significant role in facilitating communication and content sharing. However, the exponential rise in user-generated content has led to challenges in maintaining a respectful online environment.…

Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This paper introduces Prefix Probing, a black-box harmful content…

This paper aims to help structure the risk landscape associated with large-scale Language Models (LMs). In order to foster advances in responsible innovation, an in-depth understanding of the potential risks posed by these models is needed.…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…

Dataset curation has become a basis for strong large language model (LLM) performance. While various rule-based filtering heuristics exist for English and multilingual datasets, model-based filtering techniques have primarily focused on…

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Prompt-based probing has been widely used in evaluating the abilities of pretrained language models (PLMs). Unfortunately, recent studies have discovered such an evaluation may be inaccurate, inconsistent and unreliable. Furthermore, the…