The Impact of Editorial Intervention on Detecting Native Language Traces

• URL: http://arxiv.org/abs/2605.10216v1
• Date: Mon, 11 May 2026 08:58:08 GMT
• Title: The Impact of Editorial Intervention on Detecting Native Language Traces
• Abstract summary: Native Language Identification (NLI) is the task of determining an author's native language (L1) from their non-native writings.<n>With the advent of human-AI co-authorship, non-native texts are routinely corrected and rewritten by large language models.<n>We investigate the robustness of L1 traces across increasing degrees of editorial intervention.
• Score: 1.6210510806456278
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Native Language Identification (NLI) is the task of determining an author's native language (L1) from their non-native writings. With the advent of human-AI co-authorship, non-native texts are routinely corrected and rewritten by large language models, fundamentally altering the linguistic features NLI models depend on. In this paper, we investigate the robustness of L1 traces across increasing degrees of editorial intervention. By processing 450 essays from the Write & Improve 2024 corpus through varying levels of grammatical error correction (GEC) and paraphrasing, we demonstrate that L1 attribution does not entirely depend on surface-level errors. Instead, the detection models leverage deeper L1 features: unidiomatic lexico-semantic choices, pragmatic transfer, and the author's underlying cultural perspective. We find that minimal edits preserve these structural traces and maintain high profiling accuracy. In contrast, fluency edits and paraphrasing normalize these L1 features, leading to a severe degradation in performance.

Related papers

• Style as a Confound: False Positives in AI Detection of Non-Native Academic Writing [3.9444299467643025]
  We examined 135,389 document pairs from a professional English editing service.<n>For the 13 AI text detectors, FPRs for human-written texts varied widely, from 0.0% to 100.0%.<n>The findings identify professional editing style as a key confounding variable in AI detector outputs.
  arXiv  Detail & Related papers  (2026-08-27T07:05:31Z)
• Accurate but Natural? Diagnosing Grammatical and Idiomatic Gaps in Japanese EFL Writing [0.0]
  This study introduces a layered LLM-correction pipeline that isolates structural errors from unnaturalness.<n>Applying the overused-based CEFR-J grammar extractor, we quantify two diagnostic measures: accuracy gaps and idiomatic gaps.<n>Results reveal distinct patterns: definite articles, third-person singular -s, and modals (would, could) exhibit significant accuracy difficulties.<n>A two-dimensional instructional typology maps error rates against idiomatic gaps, distinguishing accurate but grammar items from error-prone or avoided complex forms.
  arXiv  Detail & Related papers  (2026-08-10T08:42:06Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• RILEC: Detection and Generation of L1 Russian Interference Errors in English Learner Texts [1.4837169131671546]
  L1 interference refers to errors influenced by a speaker's first language, such as using stadion instead of stadium.<n>We introduce RILEC, a large-scale dataset of over 18,000 sentences, combining expert-annotated data from REALEC with synthetic examples generated through rule-based and neural augmentation.<n>We propose a framework for generating L1-motivated errors using generative language models optimized with PPO, prompt-based control, and rule-based patterns.
  arXiv  Detail & Related papers  (2026-03-07T22:33:22Z)
• Robust Native Language Identification through Agentic Decomposition [23.899157231471104]
  Large language models (LLMs) often achieve high performance in native language identification (NLI) benchmarks by leveraging superficial contextual clues.<n>We show that such a strategy is unreliable and model predictions can be easily altered by misleading hints.<n>We introduce an agentic NLI pipeline inspired by forensic linguistics, where specialized agents accumulate and categorize diverse linguistic evidence.
  arXiv  Detail & Related papers  (2025-09-20T12:38:03Z)
• LLM-based Translation Inference with Iterative Bilingual Understanding [52.46978502902928]
  We propose a novel Iterative Bilingual Understanding Translation method based on the cross-lingual capabilities of large language models (LLMs)<n>The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately.<n>The proposed IBUT outperforms several strong comparison methods.
  arXiv  Detail & Related papers  (2024-10-16T13:21:46Z)
• Native Language Identification with Large Language Models [60.80452362519818]
  We show that GPT models are proficient at NLI classification, with GPT-4 setting a new performance record of 91.7% on the benchmark11 test set in a zero-shot setting. We also show that unlike previous fully-supervised settings, LLMs can perform NLI without being limited to a set of known classes.
  arXiv  Detail & Related papers  (2023-12-13T00:52:15Z)
• Cross-Lingual Knowledge Editing in Large Language Models [73.12622532088564]
  Knowledge editing has been shown to adapt large language models to new knowledge without retraining from scratch. It is still unknown the effect of source language editing on a different target language. We first collect a large-scale cross-lingual synthetic dataset by translating ZsRE from English to Chinese.
  arXiv  Detail & Related papers  (2023-09-16T11:07:52Z)
• Turkish Native Language Identification V2 [1.7802147489386628]
  This paper presents the first application of Native Language Identification (NLI) for the Turkish language.<n>We analyze a corpus of texts written by native speakers of Albanian, Arabic and Persian.<n>Our models achieve promising results, and we analyze the most predictive features to reveal L1-specific transfer effects.
  arXiv  Detail & Related papers  (2023-07-27T13:28:31Z)
• We're Afraid Language Models Aren't Modeling Ambiguity [136.8068419824318]
  Managing ambiguity is a key part of human language understanding. We characterize ambiguity in a sentence by its effect on entailment relations with another sentence. We show that a multilabel NLI model can flag political claims in the wild that are misleading due to ambiguity.
  arXiv  Detail & Related papers  (2023-04-27T17:57:58Z)
• Morphologically Aware Word-Level Translation [82.59379608647147]
  We propose a novel morphologically aware probability model for bilingual lexicon induction. Our model exploits the basic linguistic intuition that the lexeme is the key lexical unit of meaning.
  arXiv  Detail & Related papers  (2020-11-15T17:54:49Z)

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.