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.
Downloads of paraphrase-multilingual-MiniLM-L12-v2 have moved +42.5% over the trailing thirty days. That is a slight downtrend, consistent with normal cooling as newer models compete for the same workloads. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
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.
Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data
arXiv:2506.02018v2 Announce Type: replace Abstract: Paraphrasing re-expresses meaning to enhance applications like text simplification, machine translation, and question-answering. Specific paraphrase types facilitate accurate semantic analysis and robust language models. However, existing paraphras
Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
arXiv:2605.31393v1 Announce Type: cross Abstract: Sign language translation (SLT) remains constrained by limited paired sign-video/text corpora and heavy-tailed target vocabularies. We study target-side augmentation in which GPT-4o generates controlled paraphrase variants of reference sentences whil
Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline
arXiv:2605.27440v1 Announce Type: cross Abstract: Small changes to how a buyer phrases a question -- "best CRM" vs "top CRM" vs "best CRM for a SaaS startup" -- produce substantially different brand recommendations from AI assistants. Across ~6,000 paraphrase runs and ~6,000 same-prompt rerun contro
SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
arXiv:2605.25796v1 Announce Type: 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 signals by
Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization
arXiv:2604.23135v2 Announce Type: replace Abstract: Lean 4 autoformalization has become increasingly popular in recent years, with frontier language models and open-weight autoformalizers now producing valid formalizations of mathematical theorems. However, these evaluations often rely on single can
Paraphrase-Induced Output-Mode Collapse: When LLMs Break Character Under Semantically Equivalent Inputs
arXiv:2605.04665v2 Announce Type: replace Abstract: When the substantive content of a request is rewritten, do large language models still answer in the format the original task asked for? We find that they often do not, even at temperature zero. On a 150-query evaluation over five compact 2025-era
