Characterising Toxicity in Generative Large Language Models
In recent years, the advent of the attention mechanism has significantly advanced the field of natural language processing (NLP), revolutionizing text processing and text generation. This has come about through transformer-based decoder-only architectures, which have become ubiquitous in NLP due to their impressive text processing and generation capabilities. Despite these breakthroughs, language models (LMs) remain susceptible to generating undesired outputs: inappropriate, offensive, or otherwise harmful responses. We will collectively refer to these as ``toxic'' outputs. Although methods like reinforcement learning from human feedback (RLHF) have been developed to align model outputs with human values, these safeguards can often be circumvented through carefully crafted prompts. Therefore, this paper examines the extent to which LLMs generate toxic content when prompted, as well as the linguistic factors -- both lexical and syntactic -- that influence the production of such outputs in generative models.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningText GenerationSimilar Papers 제목 키워드 기반
ToViLaG: Your Visual-Language Generative Model is Also An Evildoer
Warning: this paper includes model outputs showing offensive content. Recent large-scale Visual-Language Generative Models (VLGMs) have achieved unprecedented improvement in multimodal image/text generation. However, the…
Text GenerationRecourse for reclamation: Chatting with generative language models
Researchers and developers increasingly rely on toxicity scoring to moderate generative language model outputs, in settings such as customer service, information retrieval, and content generation. However, toxicity scori…
Information RetrievalLanguage ModelingLanguage ModellingRetrievalCross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work …
Cross-Lingual TransferText GenerationToxicity Detection with Generative Prompt-based Inference
Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a long-known risk that language models (LMs),…
Language ModelingLanguage ModellingPrompt EngineeringCleanComedy: Creating Friendly Humor through Generative Techniques
Humor generation is a challenging task in natural language processing due to limited resources and the quality of existing datasets. Available humor language resources often suffer from toxicity and duplication, limiting…