Adobe secures US patent for fine-tuning language models to reduce structured data representations.
The filing
Adobe Inc. received a US grant on November 10, 2026 for a system that uses a fine-tuned language model to identify and extract relevant portions of structured data. The invention addresses the need to efficiently reduce data representations by training a model on structured data, associated queries, and the specific portions of that data relevant to each query.
This filing’s full text wasn’t read for this issue, so its claims and the applicant’s background aren’t shown. Both are in the record, under Sources.