Related papers: STAND-Guard: A Small Task-Adaptive Content Moderat…

Large language models (LLMs) remain vulnerable to misalignment and jailbreaks, making external safeguards like moderation filters essential, yet existing filters often focus narrowly on safety, falling short of the broader alignment needs…

The trend towards large language models (LLMs) for guardrailing against undesired behaviors is increasing and has shown promise for censoring user inputs. However, increased latency, memory consumption, hosting expenses and non-structured…

Online communities rely on a mix of platform policies and community-authored rules to define acceptable behavior and maintain order. However, these rules vary widely across communities, evolve over time, and are enforced inconsistently,…

The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and…

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

Finding appropriate prompts for the specific task has become an important issue as the usage of Large Language Models (LLM) has expanded. Reinforcement Learning (RL) is widely used for prompt tuning, but its inherent instability and…

Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue…

Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models could acquire superior performance on few-shot image…

AI Safety Moderation (ASM) classifiers are designed to moderate content on social media platforms and to serve as guardrails that prevent Large Language Models (LLMs) from being fine-tuned on unsafe inputs. Owing to their potential for…

With significant advances in generative AI, new technologies are rapidly being deployed with generative components. Generative models are typically trained on large datasets, resulting in model behaviors that can mimic the worst of the…

The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructures, can effectively fine-tune LLMs, while individual…

We introduce HTLM, a hyper-text language model trained on a large-scale web crawl. Modeling hyper-text has a number of advantages: (1) it is easily gathered at scale, (2) it provides rich document-level and end-task-adjacent supervision…

As modern networks grow in scale and complexity, manual configuration becomes increasingly inefficient and prone to human error. While intent-driven self-configuration using large language models has shown significant promise, such models…

Content generation conditioning on users's readability is an important application for personalization. In an era of large language models (LLMs), readability-controlled text generation based on LLMs has become increasingly important. This…

Though safety alignment has been applied to most large language models (LLMs), LLM service providers generally deploy a subsequent moderation as the external safety guardrail in real-world products. Existing moderators mainly practice a…

Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious…

Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on general safety and overlook cultural context. In this work, we introduce FanarGuard, a bilingual…

In this work, we explore "prompt tuning", a simple yet effective mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks. Unlike the discrete text prompts used by GPT-3, soft prompts…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

The rise of short-form videos on platforms like TikTok has brought new challenges in safeguarding young viewers from inappropriate content. Traditional moderation methods often fall short in handling the vast and rapidly changing landscape…