Model Detail
paraphrase-multilingual-MiniLM-L12-v2
—paraphrase-multilingual-MiniLM-L12-v2 is a large language model with 59M parameters released by SBERT. The model is registered under the sentence-similarity pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
paraphrase-multilingual-MiniLM-L12-v2 ships with 59M parameters. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
paraphrase-multilingual-MiniLM-L12-v2 is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
arXiv:2603.28301v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models achieve strong performance in robotic manipulation by leveraging pre-trained vision-language backbones. However, in downstream robotic settings, they are typically fine-tuned with limited data, leading to overfit
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
arXiv:2605.25796v3 Announce Type: replace-cross Abstract: Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark si
Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
arXiv:2605.31393v2 Announce Type: replace-cross Abstract: Sign language translation (SLT) remains constrained by the limited availability of paired sign-video/text corpora and by the heavy-tailed vocabularies typical of real-world datasets. We study a target-side augmentation strategy in which a lar
Deja Vu at Scale: Paraphrase-Robust Detection of Duplicate Gherkin Steps in Behaviour-Driven Software Testing with Sentence-Transformer Embeddings and a 1.1M-Step Open Benchmark
arXiv:2604.20462v3 Announce Type: replace-cross Abstract: Context. Behaviour-Driven Development (BDD) suites in Gherkin accumulate step-text duplication with documented maintenance cost. Prior detectors either require runnable tests or are single-organisation, leaving a gap: a static, paraphrase-rob
Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion
arXiv:2606.10099v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns about misuse such as plagiarism, misinformation, and automated influence operations, motivating the need for robust detectors. Recent work has shown that neural representations
