Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge. While LLMs are trained to write like humans, we hypothesize that this training leaves an indelible mark. LLMs develop a particularly strong aversion to token repetition very early in training. This bias persists as a''Vestigial Heuristic''(a developmental artifact) that is activated in LLM-generated text, separating LLM from human writing. To probe this phenomenon, we introduce Telescope Perplexity, a metric that evaluates the token repetition of the model, $P(s_i | s_{1:i})$ . Our empirical investigation reveals that the Telescope Perplexity signature emerges early in pre-training, and Telescope Perplexity empirically enables highly effective zero-shot LLM detection. We show state-of-the-art or competitive performance across diverse datasets (including modern evaluation sets we introduce), reference models, and perturbation schemes with greater efficiency than other methods.
It is proposed that modulating the decoding temperature and monitoring how the probability distributions respond can better probe the intrinsic discrepancies between two types of text to better probe the intrinsic discrepancies between two types of text.
Shixuan Ma, Jiahao Li, Zhendong Mao et al.· Annual Meeting of the Associ...· 2 citations
The key idea is to smooth adjacent token scores to reduce their variability, while using an adaptive Lepski-type rule to select the bandwidth according to the local authorship structure, and the proposed method achieves favorable mean square error performance in estimating the underlying signal.
Yangjun Lu, Hongyi Zhou, Fabian Spill et al.· 0 citations
This work analyses the linearity and quality of MGT representations and shows that simple linear probes outperform a wide range of detectors while being substantially more sample-efficient, and demonstrates the potential of linear probes as as robust and sample-efficient MGT detectors.
Gerrit Quaremba, Hanqi Yan, E. Black et al.· 0 citations
The core of VaryBalance is that, compared to LLM-generated texts, there is a greater difference between human texts and their rewritten version via LLMs, and quantifies this through Mean Squared Deviation and distinguishes human texts and LLM-generated texts.
Xuecong Li, Xiaohong Li, Qiang Hu et al.· 0 citations
Across several benchmarks, it is shown that a plain, fully fine-tuned RoBERTa matches or exceeds the specialized detectors those benchmarks are built around, suggesting that progress in AI-generated text detection should be measured not only by in-distribution performance, but also by robustness under distribution shift.
Zhuoer Shen, Mingyi Wang, Shaofeng Zou et al.· 0 citations
EchoPrompt is proposed, a training-free detector based on latent prompt restoration that achieves state-of-the-art performance among zero-shot detectors while maintaining strong robustness across challenging evaluation settings.
Hongrui Bao, Yubing Ren, Yanan Cao et al.· 0 citations