Related papers: Less is More: Sparse Watermarking in LLMs with Enh…
In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on…
Detecting machine-generated text is essential for transparency and accountability when deploying large language models (LLMs). Among detection approaches, watermarking is a statistically reliable method by design -- it embeds detectable…
With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability…
Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…
Watermarking is a principled approach for tracing the provenance of large language model (LLM) outputs, but its deployment in practice is hindered by inference inefficiency. Speculative sampling accelerates inference, with efficiency…
Digital watermarking is a promising solution for mitigating some of the risks arising from the misuse of automatically generated text. These approaches either embed non-specific watermarks to allow for the detection of any text generated by…
We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this paper, we propose a rigorous theoretical framework to…
Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which focus on preserving…
Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This…
As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms. Existing watermark techniques are shown effective in…
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the…
Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time watermarking, to protect…
The task of discerning between generated and natural texts is increasingly challenging. In this context, watermarking emerges as a promising technique for ascribing generated text to a specific model. It alters the sampling generation…
As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing…
Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent…
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…
The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To address this issue, watermarking methods have been proposed to embed identifiable multi-bit…
We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark design space by…
Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…
Large Language Models (LLMs) excel in various applications, including text generation and complex tasks. However, the misuse of LLMs raises concerns about the authenticity and ethical implications of the content they produce, such as…