Now in V3.0 — the new industry-leading bar for pre-publication Chinese correction, across text, video subtitles, audio transcription, and image OCR, built for production scale.
Yanlan is a Chinese proofreading system powered by Yanlan-LLM V3.0, a language model trained with a multi-stage RL pipeline, built around the lived constraints of production deployment: false-alarm rates that don't waste editors' time, throughput that handles a daily news pipeline, and a cost profile that runs on a single mid-range GPU. The model handles plain text but also reads video subtitles, audio transcripts, and image OCR — so the corrections happen where the content lives.
Explore the document layout, subtitle frames, and review suggestions. Yanlan-expand expands individual character differences into phrase-level highlights, keeping each correction in context.
Sample notice for text review
Yanlan connects into the subtitle pipeline and audits every line as it passes — typos, mis-recognised characters, mismatched terms — at 99%+ accuracy and roughly 1–5 seconds per minute of video. Already in use at editorial desks producing multilingual subtitles daily.
ASR transcripts arrive noisy. Yanlan reads them with the audio context in mind, fixes mis-heard homophones, normalises proper nouns, and respects dialectal forms instead of flattening them. 96%+ accuracy across major Mandarin variants.
Beyond text: Yanlan includes a face-verification head trained for compliance review on broadcast and streaming content. 98%+ recognition accuracy with a 20–30× speedup over the manual review pipeline.
Anchored to a corpus of 16,740 Chinese laws and regulations with daily auto-updates, Yanlan flags content that conflicts with current rules — useful for legal review on government, media, and education output.
All eight weighted headline metrics improve over V2.0, with 43 of 47 direct comparisons won. The full release brief separates the evidence, methodology, and deployment implications from the product overview.
Accuracy is only half the requirement. A corrector that is accurate but slow cannot enter production; one that is fast but costly cannot pass a budget review. Yanlan clears both thresholds on a single mid-range GPU, measured against the strongest commercial baselines available.
Yanlan runs as a multimodal perception layer that normalises text, audio, image, and video subtitles into a common token stream, then routes through a classifier that selects between a central dictionary of standard Chinese, a custom dictionary tuned per deployment, and a correction model. A post-processing integration layer merges results before output.
Training is multi-stage RL on top of a Chinese-tuned base: supervised fine-tuning on human-verified corrections, then RL with editorial rewards that explicitly penalise false positives — that last step is what gets the false-alarm rate down to 0.5%.
Already serving news and publishing organizations, government communications, financial and legal compliance, and broadcast media. Enterprise and government teams: contact us to evaluate Yanlan on your own content.
Try Yanlan → Contact sales