Different Time, Different Language: Revisiting the Bias Against Non-Native Speakers in GPT Detectors

• URL: http://arxiv.org/abs/2602.05769v1
• Date: Thu, 05 Feb 2026 15:31:24 GMT
• Title: Different Time, Different Language: Revisiting the Bias Against Non-Native Speakers in GPT Detectors
• Abstract summary: We show that the perplexity of texts from non-native speakers of Czech is not lower than that of native speakers.<n>We examine detectors from three separate families and find no systematic bias against non-native speakers.
• Score: 0.9440878004466183
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-based assistants have been widely popularised after the release of ChatGPT. Concerns have been raised about their misuse in academia, given the difficulty of distinguishing between human-written and generated text. To combat this, automated techniques have been developed and shown to be effective, to some extent. However, prior work suggests that these methods often falsely flag essays from non-native speakers as generated, due to their low perplexity extracted from an LLM, which is supposedly a key feature of the detectors. We revisit these statements two years later, specifically in the Czech language setting. We show that the perplexity of texts from non-native speakers of Czech is not lower than that of native speakers. We further examine detectors from three separate families and find no systematic bias against non-native speakers. Finally, we demonstrate that contemporary detectors operate effectively without relying on perplexity.

Related papers

• SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection [51.096014381455454]
  Self-supervised learning-based speech encoders struggle to generalize across unseen speakers.<n>Speaker entanglement causes detectors to exploit speaker-specific correlations rather than artifact-related cues.<n>We introduce SNAP, a speaker-nulling framework, to mitigate this reliance.
  arXiv  Detail & Related papers  (2026-03-21T07:05:30Z)
• Thai Semantic End-of-Turn Detection for Real-Time Voice Agents [0.3499870393443268]
  Traditional audio-silence end-pointers add hundreds of milliseconds of delay and fail under hesitations or language-specific phenomena.<n>We present to our knowledge, the first systematic study of Thai text-only end-of-turn (EOT) detection for real-time agents.
  arXiv  Detail & Related papers  (2025-10-05T03:31:59Z)
• Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically [58.019484208091534]
  Cross-lingual alignment in pretrained language models (LMs) has enabled efficient transfer in text-based LMs.<n>It remains an open question whether findings and methods from text-based cross-lingual alignment apply to speech.
  arXiv  Detail & Related papers  (2025-05-26T07:21:20Z)
• What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection [7.555970188701627]
  We introduce transcript-level adversarial attacks against open-source and commercial anti-spoofing detectors.<n>Attack success rates surpass 60% on several open-source detector-voice pairs, and one commercial detection accuracy drops from 100% on synthetic audio to just 32%.<n>Results highlight the need to move beyond purely acoustic defenses and account for linguistic variation in the design of robust anti-spoofing systems.
  arXiv  Detail & Related papers  (2025-05-23T06:06:37Z)
• Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors [77.82885394684202]
  We propose textbfContrastive textbfParaphrase textbfAttack (CoPA), a training-free method that effectively deceives text detectors.<n>CoPA constructs an auxiliary machine-like word distribution as a contrast to the human-like distribution generated by large language models.<n>Our theoretical analysis suggests the superiority of the proposed attack.
  arXiv  Detail & Related papers  (2025-05-21T10:08:39Z)
• ESPERANTO: Evaluating Synthesized Phrases to Enhance Robustness in AI Detection for Text Origination [1.8418334324753884]
  This paper introduces back-translation as a novel technique for evading detection. We present a model that combines these back-translated texts to produce a manipulated version of the original AI-generated text. We evaluate this technique on nine AI detectors, including six open-source and three proprietary systems.
  arXiv  Detail & Related papers  (2024-09-22T01:13:22Z)
• Towards Unsupervised Speech Recognition Without Pronunciation Models [57.222729245842054]
  In this article, we tackle the challenge of developing ASR systems without paired speech and text corpora.<n>We experimentally demonstrate that an unsupervised speech recognizer can emerge from joint speech-to-speech and text-to-text masked token-infilling.<n>This innovative model surpasses the performance of previous unsupervised ASR models under the lexicon-free setting.
  arXiv  Detail & Related papers  (2024-06-12T16:30:58Z)
• Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases [79.07111754406841]
  This work proposes using contrastive evaluation to measure the ability of direct S2TT systems to disambiguate utterances where prosody plays a crucial role. Our results clearly demonstrate the value of direct translation systems over cascade translation models.
  arXiv  Detail & Related papers  (2024-02-01T14:46:35Z)
• Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion [43.97757799751764]
  Foreign accent conversion (FAC) is a special application of voice conversion (VC) which aims to convert the accented speech of a non-native speaker to a native-sounding speech with the same speaker identity. In this work, we evaluate three recently proposed methods for ground-truth-free FAC, where all of them aim to harness the power of sequence-to-sequence (seq2seq) and non-parallel VC models to properly convert the accent and control the speaker identity.
  arXiv  Detail & Related papers  (2023-09-05T11:22:08Z)
• Red Teaming Language Model Detectors with Language Models [114.36392560711022]
  Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
  arXiv  Detail & Related papers  (2023-05-31T10:08:37Z)
• GPT detectors are biased against non-native English writers [13.853577885942514]
  We evaluate the performance of several widely-used GPT detectors using writing samples from native and non-native English writers. Our findings reveal that these detectors consistently misclassify non-native English writing samples as AI-generated, whereas native writing samples are accurately identified.
  arXiv  Detail & Related papers  (2023-04-06T01:51:15Z)
• In search of strong embedding extractors for speaker diarisation [49.7017388682077]
  We tackle two key problems when adopting EEs for speaker diarisation. First, the evaluation is not straightforward because the features required for better performance differ between speaker verification and diarisation. We show that better performance on widely adopted speaker verification evaluation protocols does not lead to better diarisation performance. We propose two data augmentation techniques to alleviate the second problem, making embedding extractors aware of overlapped speech or speaker change input.
  arXiv  Detail & Related papers  (2022-10-26T13:00:29Z)
• Cross-Lingual Speaker Identification Using Distant Supervision [84.51121411280134]
  We propose a speaker identification framework that addresses issues such as lack of contextual reasoning and poor cross-lingual generalization. We show that the resulting model outperforms previous state-of-the-art methods on two English speaker identification benchmarks by up to 9% in accuracy and 5% with only distant supervision.
  arXiv  Detail & Related papers  (2022-10-11T20:49:44Z)

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.