Related papers: When Personalization Tricks Detectors: The Feature…

Large Language Models (LLMs) have demonstrated exceptional performance on a range of downstream NLP tasks by generating text that closely resembles human writing. However, the ease of achieving this similarity raises concerns from potential…

Our work addresses the critical issue of distinguishing text generated by Large Language Models (LLMs) from human-produced text, a task essential for numerous applications. Despite ongoing debate about the feasibility of such…

The rapid development of large language models (LLMs) has significantly improved the generation of fluent and convincing text, raising concerns about their potential misuse on social media platforms. We present a comprehensive methodology…

AI-text detectors achieve high accuracy on in-domain benchmarks, but often struggle to generalize across different generation conditions such as unseen prompts, model families, or domains. While prior work has reported these generalization…

Large Language Models (LLMs) have attained human-level fluency in text generation, which complicates the distinguishing between human-written and LLM-generated texts. This increases the risk of misuse and highlights the need for reliable…

The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to…

In the era of large language models generating high quality texts, it is a necessity to develop methods for detection of machine-generated text to avoid harmful use or simply due to annotation purposes. It is, however, also important to…

Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…

Machine-Generated Text (MGT) detection aims to identify a piece of text as machine or human written. Prior work has primarily formulated MGT detection as a binary classification task over an entire document, with limited work exploring…

Interpreting data is central to modern research. Large language models (LLMs) show promise in providing such natural language interpretations of data, yet simple feature extraction methods such as prompting often fail to produce accurate…

Personalized text generation aims to infer users' writing style preferences from their historical texts and generate outputs that faithfully reflect these stylistic characteristics. Existing solutions primarily adopt two paradigms:…

Personalization with retrieval-augmented generation (RAG) often fails to capture fine-grained features of authors, making it hard to identify their unique traits. To enrich the RAG context, we propose providing Large Language Models (LLMs)…

With the advancement in capabilities of Large Language Models (LLMs), one major step in the responsible and safe use of such LLMs is to be able to detect text generated by these models. While supervised AI-generated text detectors perform…

The increasing availability of large language models (LLMs) has raised concerns about their potential misuse in online learning. While tools for detecting LLM-generated text exist and are widely used by researchers and educators, their…

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…

With the surge of large language models (LLMs) and their ability to produce customized output, style-personalized text generation--"write like me"--has become a rapidly growing area of interest. However, style personalization is highly…

Synthetic data has the potential to improve the performance, training efficiency, and privacy of real training examples. Nevertheless, existing approaches for synthetic text generation are mostly heuristics and cannot generate…

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

The widespread adoption of large language models (LLMs) makes it important to recognize their strengths and limitations. We argue that in order to develop a holistic understanding of these systems we need to consider the problem that they…

The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. While recent studies explore leveraging internal representations of language models to…