相关论文: Watermarking LLM-Generated Datasets in Downstream …

Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations…

Although large language models (LLMs) have advanced the state-of-the-art in NLP significantly, deploying them for downstream applications is still challenging due to cost, responsiveness, control, or concerns around privacy and security. As…

As large language models (LLMs) generate increasingly human-like text, watermarking has emerged as a promising solution for reliable attribution beyond mere detection. While multi-bit watermarking enables richer provenance encoding,…

Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models. However, unauthorized use of knowledge distillation takes unfair advantage of the considerable effort…

As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed. At the same…

Large language models (LLMs) have facilitated the generation of high-quality, cost-effective synthetic data for developing downstream models and conducting statistical analyses in various domains. However, the increased reliance on…

Programmatic weak supervision methodologies facilitate the expedited labeling of extensive datasets through the use of label functions (LFs) that encapsulate heuristic data sources. Nonetheless, the creation of precise LFs necessitates…

High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation…

The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform many tasks, such models are often fine-tuned to improve their performance on…

The proliferation of open-source code and large language models (LLMs) for code generation has amplified the risks of unauthorized reuse and intellectual property infringement. Source code watermarking offers a potential solution, yet…

Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to determine the specific model used, particularly for purposes such as protecting…

Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking, has been used as a principled approach to provable detection…

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike autoregressive…

The advent of video-based Large Language Models (LLMs) has significantly enhanced video understanding. However, it has also raised some safety concerns regarding data protection, as videos can be more easily annotated, even without…

Reasoning Large Language Models (RLLMs) excelling in complex tasks present unique challenges for digital watermarking, as existing methods often disrupt logical coherence or incur high computational costs. Token-based watermarking…

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against…

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…

Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set. We introduce a solution to this problem by…

The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents…