Base Models Look Human to AI Detectors
Computer Science > Computation and Language arXiv:2605.19516 (cs) [Submitted on 19 May 2026] Title:Base Models Look Human To AI Detectors Authors:Yixuan Even Xu, Ziqian Zhong, Aditi Raghunathan, Fei Fang, J. 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.
- ▪Computer Science > Computation and Language arXiv:2605.19516 (cs) [Submitted on 19 May 2026] Title:Base Models Look Human To AI Detectors Authors:Yixuan Even Xu, Ziqian Zhong, Aditi Raghunathan, Fei Fang, J.
- ▪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.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,607 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv.org |
| Canonical URL | https://arxiv.org/abs/2605.19516 |
| Publication time | Wed, 12 Aug 2026 13:55:26 +0000 |
| Retrieval time | 2026-08-12T13:56:35.487Z |
| Last seen | 2026-08-12T13:56:35.487Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | jIEKtVGKIj5u · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Computation and Language arXiv:2605.19516 (cs) [Submitted on 19 May 2026] Title:Base Models Look Human To AI Detectors Authors:Yixuan Even Xu, Ziqian Zhong, Aditi Raghunathan, Fei Fang, J. Zico Kolter View a PDF of the paper titled Base Models Look Human To AI Detectors, by Yixuan Even Xu and 4 other authors View PDF HTML (experimental) 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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
