Related papers: Watermarking Makes Language Models Radioactive

To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection.…

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Misinformation regarding climate change is a key roadblock in addressing one of the most serious threats to humanity. This paper investigates factual accuracy in large language models (LLMs) regarding climate information. Using true/false…

Social media influence campaigns pose significant challenges to public discourse and democracy. Traditional detection methods fall short due to the complexity and dynamic nature of social media. Addressing this, we propose a novel detection…

We propose a methodology for planting watermarks in text from an autoregressive language model that are robust to perturbations without changing the distribution over text up to a certain maximum generation budget. We generate watermarked…

Watermark algorithms for large language models (LLMs) have achieved extremely high accuracy in detecting text generated by LLMs. Such algorithms typically involve adding extra watermark logits to the LLM's logits at each generation step.…

The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be…

Reinforcement learning (RL) post-training has shown to improve reasoning in large language models (LLMs). However, there has been little exploration on the problem of data contamination in RL post-training, potentially undermining…

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…

Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying…

Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but pose risks of inadvertently exposing copyrighted or proprietary data, especially when such data is used for training but not intended for distribution.…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Text watermarking algorithms for large language models (LLMs) can effectively identify machine-generated texts by embedding and detecting hidden features in the text. Although the current text watermarking algorithms perform well in most…

The powerful ability to understand, follow, and generate complex language emerging from large language models (LLMs) makes LLM-generated text flood many areas of our daily lives at an incredible speed and is widely accepted by humans. As…

Detecting life-threatening language is essential for safeguarding individuals in distress, promoting mental health and well-being, and preventing potential harm and loss of life. This paper presents an effective approach to identifying…

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible…

It has been shown that finetuned transformers and other supervised detectors effectively distinguish between human and machine-generated text in some situations arXiv:2305.13242, but we find that even simple classifiers on top of n-gram and…

In a data-driven world, datasets constitute a significant economic value. Dataset owners who spend time and money to collect and curate the data are incentivized to ensure that their datasets are not used in ways that they did not…

Reliable evaluation is essential in machine learning research, yet methodological flaws-particularly data leakage-continue to undermine the validity of reported results. In this work, we investigate whether large language models (LLMs) can…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…