VietAIDetector is an open‑source, zero‑shot tool for detecting Vietnamese AI‑generated text. It offers a Gradio web interface that accepts raw Vietnamese text, common file formats, scanned documents, and very long texts beyond typical LLM context limits. Built on a Vietnamese‑specific language model, it outperforms existing English‑centric methods on out‑of‑domain datasets and lets users choose detection thresholds based on F1, accuracy, or TPR@0.05FPR, with results viewable or downloadable as a PDF report.
By Trieu Hai Nguyen, Van-Dung Hoang
VietPrism is a newly released, large‑scale Vietnamese speech corpus that combines 993.4 hours of real utterances from 1,262 verified speakers with 3.1 k hours of synthetic spoof speech. It uniquely offers transcripts, consistent speaker identities, five dialect groups, and extensive Vietnamese‑English code‑switching—nearly half of the corpus—while pairing each spoof with a matched bona fide utterance. The dataset enables controlled evaluation of deep‑fake detection models, revealing significant variability in detector performance across dialects and speaker similarity.
By Minh Hoang, Thai Le
arXiv:2607. 04061v1 Announce Type: cross Abstract: Distinguishing Large Language Model (LLM) generated text from human writing is a critical and difficult challenge.
By Christopher Nassif, Josh F. Cooper
Vision‑Language Models (VLMs) are increasingly replacing traditional OCR for document understanding, but this study shows they often rewrite imperfect text into more plausible forms, a flaw that clean‑text OCR benchmarks miss. The authors created FaithC4, a multilingual perturbation benchmark of 1,455 single‑page documents with scramble, random substitution, and visually similar substitution attacks, and evaluated 15 systems across general‑purpose VLMs, OCR‑specialized VLMs, and traditional OCR pipelines. Results reveal that general‑purpose VLMs suffer up to 6.9 WER points under perturbation, OCR‑specialized VLMs 0.1–3.4 points, and traditional OCR less than 0.8 points on English; probing Qwen3‑VL‑4B shows rewriting occurs only when a perturbed word’s final‑layer representation remains close to the original, with short words (4–6 characters) rewritten up to 10% of the time.
whyItMatters":"The findings highlight a critical limitation of VLMs in document transcription, underscoring the need for robust evaluation benchmarks that capture rewriting behavior beyond clean‑text accuracy."
By Gwang Gook Lee, Kenan Emir Ak, Jay Mohta, Yan Xu, Dimitrios Dimitriadis
The paper introduces a controlled benchmark for evaluating large language models (LLMs) on key‑value pair extraction from documents with varying levels of OCR noise. It tests 136 configurations across five instruction‑tuned open‑weight LLMs, three datasets, and four text‑quality conditions, using deterministic decoding to generate 17,688 document‑level inferences. The study finds that clean‑text performance does not reliably predict real‑world robustness, model rankings can reverse under noisy conditions, and few‑shot demonstrations do not always improve accuracy, highlighting reliability risks in OCR‑to‑LLM pipelines.
By Zahra Anvari
The paper reports that scene text recognition models, while achieving 89–97% accuracy on standard benchmarks, perform significantly worse on rare word–trigram combinations, with a 10–18 point drop in accuracy at the rare‑word/rare‑trigram corner across multiple languages and models. Scaling the vision backbone improves overall accuracy but does not alleviate this corner‑specific deficit. The authors identify the autoregressive decoder’s lexical prior as the root cause and show that architectural changes—specifically moving from autoregressive to CTC decoding—yield the largest improvement for these rare compositions.
By Genpei Zhang
SpanCalib-VLM is a hybrid system for detecting hallucinated text spans in Vision‑Language Models. It combines a multimodal sequence tagger (XLM‑RoBERTa‑Large + SigLIP) with a fine‑tuned generative VLM (Qwen3.5‑4B‑SHROOM‑SFT) and uses a Union‑Calibrated Fusion strategy to re‑score candidate spans. On the SHROOM‑Visions English evaluation split, the ensemble achieves a Pearson calibration correlation of 0.41, an overall IoU of 0.39, a clean‑response IoU of 0.91, and a detection accuracy of 70.7%.
By Amanuel Gizachew Abebe, Yasmin Moslem
IndicDetect is a benchmark for evaluating AI‑generated text detection in Hindi, Telugu, and Tamil. It pairs curated human‑written texts with LLM‑generated counterparts across multiple domains and generators, testing detectors under domain shift, generator shift, and adversarial perturbation. The study shows that supervised neural detectors fail to generalize to unseen generators and attacks, with Hindi experiencing the greatest degradation, indicating that robustness—not peak accuracy—is the main weakness in Indic language detectors.
By Bhaskar Ganesh Devalla, Junchao Wu, Nilesh Dokuparthi, Greeshma Yaluru, Tatiana Muniz Rodriguez, Lidia S. Chao, Derek F. Wong
Translating Han-Nom manuscripts into modern Vietnamese is challenging because historical pages are often degraded, the script contains rare logographic characters, and parallel supervision is limited. We propose a multimodal RLHF preference-alignment framework that conditions Vietnamese generation on manuscript images and aligned Han-Nom source text.
In 2026, the SHROOM-Visions shared task was launched at the UncertaiNLP Workshop co‑located with EMNLP to address hallucinations in large vision‑language models. The task builds on the SHEEP dataset and asks participants to detect and classify fine‑grained hallucination spans in image‑conditioned text generation across four languages (Chinese, English, French, Italian) using a five‑class taxonomy. The competition attracted 27 teams and over 600 system submissions, with top systems achieving character‑level, label‑conditioned, and IoU scores of 0.58, 0.46, and 0.51 respectively, surpassing baselines by 30‑40 points.
By Ra\'ul V\'azquez, Aman Sinha, Chuyuan Li, Claudio Savelli, Eduardo Cal\`o, Emilio Raimond, Stella Frank, Hengyu Luo, Flavio Giobergia, Vincent Segonne, Lorenzo Vaiani, J\"org Tiedemann, Timothee Mickus
Manacá-1B is a 1.72‑billion‑parameter, open decoder‑only language model trained from scratch for Brazilian Portuguese, released with a fully containerized, reproducible training pipeline and complete logs. The authors evaluate it against nine open baselines on four Portuguese benchmarks, reporting standard errors and paired significance tests, and find that Manacá-1B outperforms smaller models on LAMBADA‑PT while remaining competitive on commonsense completion. They also uncover a tokenizer‑related evaluation pitfall that can drastically lower accuracy and provide a simple fix, releasing all code, logs, and corrected tokenizer for full reproducibility.
By Bruno Leonardo Santos Menezes, Carlos Leonardo Souza Cardoso, Fabio Andre Machado Porto
arXiv:2609.27510v1 Announce Type: cross
Abstract: Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and...
By Kaifeng Tan, Yudong Li, Linlin Shen