Base Models Look Human To AI Detectors

• URL: http://arxiv.org/abs/2605.19516v1
• Date: Tue, 19 May 2026 08:13:12 GMT
• Title: Base Models Look Human To AI Detectors
• Abstract summary: We show that generated text from base models is often judged overwhelmingly human, whereas text generated by their instruction-tuned counterparts is not.<n>We propose Humanization by Iterative Paraphrasing (HIP), a detector-agnostic pipeline that minimally fine-tunes a base model into a paraphraser and applies it iteratively.<n>Our findings suggest that current detectors are tracking artifacts of instruction tuning and local context more than any in notion of machine-generated text.
• Score: 68.7723287560362
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As AI-generated text enters the real-world at scale, institutions increasingly use commercial AI-text detectors, especially in education and academic-integrity workflows. We report a surprising empirical finding about such systems: when evaluated by GPTZero and Pangram, generated text from base models is often judged overwhelmingly human, whereas text generated by their instruction-tuned counterparts is not. Building on this observation, we propose Humanization by Iterative Paraphrasing (HIP), a detector-agnostic pipeline that minimally fine-tunes a base model into a paraphraser and applies it iteratively. Compared with the baselines we test, HIP yields a stronger trade-off between semantic preservation and detector evasion on commercial detectors. Across Llama-3 and Qwen-3 families, spanning model sizes from 0.6B to 70B, HIP consistently improves detector human-likeness. Our findings suggest that current detectors are tracking artifacts of instruction tuning and local context more than any invariant notion of machine-generated text. This, in turn, calls for detector designs that model these factors more explicitly.

Related papers

• AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection [1.373282478189168]
  We propose textscAEyeDE, an attribution-driven approach to human-AI authorship detection.<n>We show that attention-based attribution maps provide a complementary and interpretable signal for AI-generated text detection.
  arXiv  Detail & Related papers  (2026-04-13T19:30:40Z)
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring [14.887491317701997]
  This paper explores the possibility of fine-grained MGT detection under human-AI coauthoring.<n>We suggest fine-grained detectors can pave pathways toward coauthored text detection with a numeric AI ratio.<n> Empirical results show that metric-based methods struggle to conduct fine-grained detection with a 0.462 average F1 score.
  arXiv  Detail & Related papers  (2025-06-03T14:52:44Z)
• Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectors [4.7713095161046555]
  We present a pipeline to test the resilience of state-of-the-art MGT detectors to linguistically informed adversarial attacks.<n>We fine-tune language models to shift the MGT style toward human-written text (HWT)<n>This exploits the detectors' reliance on stylistic clues, making new generations more challenging to detect.
  arXiv  Detail & Related papers  (2025-05-30T12:33:30Z)
• AuthorMist: Evading AI Text Detectors with Reinforcement Learning [4.806579822134391]
  AuthorMist is a novel reinforcement learning-based system to transform AI-generated text into human-like writing.<n>We show that AuthorMist effectively reduces the detectability of AI-generated text while preserving the original meaning.
  arXiv  Detail & Related papers  (2025-03-10T12:41:05Z)
• Detecting Machine-Generated Long-Form Content with Latent-Space Variables [54.07946647012579]
  Existing zero-shot detectors primarily focus on token-level distributions, which are vulnerable to real-world domain shifts. We propose a more robust method that incorporates abstract elements, such as event transitions, as key deciding factors to detect machine versus human texts.
  arXiv  Detail & Related papers  (2024-10-04T18:42:09Z)
• DetectGPT-SC: Improving Detection of Text Generated by Large Language Models through Self-Consistency with Masked Predictions [13.077729125193434]
  Existing detectors are built on the assumption that there is a distribution gap between human-generated and AI-generated texts. We find that large language models such as ChatGPT exhibit strong self-consistency in text generation and continuation. We propose a new method for AI-generated texts detection based on self-consistency with masked predictions.
  arXiv  Detail & Related papers  (2023-10-23T01:23:10Z)
• On the Possibilities of AI-Generated Text Detection [76.55825911221434]
  We argue that as machine-generated text approximates human-like quality, the sample size needed for detection bounds increases. We test various state-of-the-art text generators, including GPT-2, GPT-3.5-Turbo, Llama, Llama-2-13B-Chat-HF, and Llama-2-70B-Chat-HF, against detectors, including oBERTa-Large/Base-Detector, GPTZero.
  arXiv  Detail & Related papers  (2023-04-10T17:47:39Z)
• Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense [56.077252790310176]
  We present a paraphrase generation model (DIPPER) that can paraphrase paragraphs, condition on surrounding context, and control lexical diversity and content reordering. Using DIPPER to paraphrase text generated by three large language models (including GPT3.5-davinci-003) successfully evades several detectors, including watermarking. We introduce a simple defense that relies on retrieving semantically-similar generations and must be maintained by a language model API provider.
  arXiv  Detail & Related papers  (2023-03-23T16:29:27Z)
• Can AI-Generated Text be Reliably Detected? [50.95804851595018]
  Large Language Models (LLMs) perform impressively well in various applications.<n>The potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their responsible use.<n>We stress-test the robustness of these AI text detectors in the presence of an attacker.
  arXiv  Detail & Related papers  (2023-03-17T17:53:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.