Related papers: Mitigating harm in language models with conditiona…

User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written…

State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…

This paper describes our approach to hierarchical multi-label detection of persuasion techniques in meme texts. Our model, developed as a part of the recent SemEval task, is based on fine-tuning individual language models (BERT,…

We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to…

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Unlocking the potential of Large Language Models (LLMs) in data classification represents a promising frontier in natural language processing. In this work, we evaluate the performance of different LLMs in comparison with state-of-the-art…

This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Human and model-generated texts can be distinguished by examining the magnitude of likelihood in language. However, it is becoming increasingly difficult as language model's capabilities of generating human-like texts keep evolving. This…

Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources. However, there are instances where we desire a model that excels in specific areas without markedly compromising performance…

Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts,…

The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models,…

While large language models (LLMs) have increasingly been applied to hate speech detoxification, the prompts often trigger safety alerts, causing LLMs to refuse the task. In this study, we systematically investigate false refusal behavior…

Writing effective prompts for large language models (LLM) can be unintuitive and burdensome. In response, services that optimize or suggest prompts have emerged. While such services can reduce user effort, they also introduce a risk: the…

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Style-conditioned data poisoning is identified as a covert vector for amplifying sociolinguistic bias in large language models. Using small poisoned budgets that pair dialectal prompts -- principally African American Vernacular English…

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their practical application in high-stake domains, such as fraud and abuse detection, remains an area that requires…

Online social platforms are beset with hateful speech - content that expresses hatred for a person or group of people. Such content can frighten, intimidate, or silence platform users, and some of it can inspire other users to commit…

Content moderation on social media platforms shapes the dynamics of online discourse, influencing whose voices are amplified and whose are suppressed. Recent studies have raised concerns about the fairness of content moderation practices,…