Get the newsletter
Adobe · AI / ML · Filed Feb 11, 2025 · USPTO published Aug 13, 2026 · Aug 13 release

Adobe Patents Technology to Catch Where AI Misreads Plain-English Commands

Adobe has patented a diagnostic system that can automatically spot the categories of plain-English questions an AI consistently gets wrong, then take steps to fix those blind spots before they reach users.

User interface displaying query accuracy metrics and AI-suggested plain-English rewrites for better results. Drawing from patent filing US 2026/0236461 A1.
User interface displaying query accuracy metrics and AI-suggested plain-English rewrites for better results.All 10 drawings ↓
Publication number
US 2026/0236461 A1(US20260236461A1)
Applicant
Adobe Inc.
Filed · Published
Feb 11, 2025 · Aug 13, 2026
Inventors
Neha Srikanth, Ani Nenkova, Victor Soares Bursztyn
Status when we published
Waiting for an examiner
Document
20 claims
US classification
704/9
Examiner
ISLAM, MOHAMMAD K (Art Unit 2653)

What Adobe's query-parsing gap detector actually does

Every time you type a plain-English question into a business tool and it runs the wrong report, something called a semantic parsing model made a mistake. These AI systems translate your words into the precise code a database can actually execute, and when they fail, the results can be silently wrong.

Adobe's patent describes a way to automatically hunt down those failure points. The system groups similar questions together, checks how often the AI gets each group right, and flags the groups where it keeps stumbling. Think of it as a teacher grading a student's tests by subject: you might find the student aces algebra but consistently bombs word problems.

Once the weak spots are identified, the system can take corrective steps, such as adding more training examples in those problem areas. The goal is a more reliable AI assistant, one that handles the full range of things you might actually ask.

From the filing · CLAIM 1
… determining, utilizing a data clustering model, clusters of semantic parsing examples according to similarities between respective predicates of the plurality of predicates; …

Translation: The system groups similar language patterns together using data clustering.

How the clustering and scoring pipeline finds weak clusters

The patent covers a four-step pipeline designed to audit and improve semantic parsing models, which are AI systems that convert natural language (a typed or spoken question) into a structured query a database or software system can run.

  • Predicate extraction: A language model reads through a library of example questions and pulls out the core action words (called predicates) from each one, things like "count," "filter by date," or "compare."
  • Clustering: A data clustering algorithm groups the example questions by how similar their predicates are, so questions about filtering end up in one bucket, questions about aggregating numbers in another, and so on.
  • Accuracy scoring: The AI model being tested generates its best structured output for each question. The system then compares those outputs to the known-correct answers and calculates a correctness score for each cluster, not just an overall average.
  • Gap identification and mitigation: Clusters with low correctness scores are flagged as robustness gaps (meaning the model is fragile in that area), and the system can automatically trigger fixes, such as generating new training data for those weak clusters.

The key insight is moving from a single overall accuracy number to a per-topic breakdown. An AI can look strong on average while completely failing a specific class of questions.

From the filing · THE ABSTRACT
… identify robustness gaps in the target semantic parsing model based on the respective correctness values and implement mitigating actions to address the identified gaps.

Translation: It pinpoints where the artificial intelligence struggles with plain English and fixes those weak spots.

What this means for AI tools that take spoken or typed commands

For anyone using a business intelligence tool, a customer-service bot, or any software that lets you ask questions in plain English, the quality of the underlying parsing model determines whether you get the right answer or a plausible-looking wrong one. A system that only checks its overall score can hide serious failures in narrow but important query types, like questions involving dates, negations, or multi-step comparisons.

Adobe's tools, including its analytics and data products, rely heavily on natural language interfaces, so a patent in this space fits a clear internal need. AI language assistants are one of the more active areas covered in plain-English patent summaries, and Adobe's filing reflects a broader industry push to move past raw accuracy benchmarks toward more targeted quality controls that catch the failures users actually experience.

Source: US 2026/0236461 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Adobe patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 10 sheets

10 drawing sheets from US 2026/0236461 A1 · click any drawing to enlarge

System architecture for natural language parsing, drawing sheet 1 from US 2026/0236461 A1
Sheet 1 System architecture for natural language parsing
Workflow for identifying AI robustness gaps, drawing sheet 2 from US 2026/0236461 A1
Sheet 2 Workflow for identifying AI robustness gaps
Pipeline for extracting query feature vectors, drawing sheet 3 from US 2026/0236461 A1
Sheet 3 Pipeline for extracting query feature vectors
Comparative evaluation of model correctness, drawing sheet 4 from US 2026/0236461 A1
Sheet 4 Comparative evaluation of model correctness
Predicting and mitigating model correctness errors, drawing sheet 5 from US 2026/0236461 A1
Sheet 5 Predicting and mitigating model correctness errors
Graphical interface for query analysis, drawing sheet 6 from US 2026/0236461 A1
Sheet 6 Graphical interface for query analysis
Clustering analysis of query difficulty, drawing sheet 7 from US 2026/0236461 A1
Sheet 7 Clustering analysis of query difficulty
Computing device software component architecture, drawing sheet 8 from US 2026/0236461 A1
Sheet 8 Computing device software component architecture
Show the other 2 sheets
Adobe Patents Technology to Catch Where AI Misreads Plain-English Commands patent drawing, sheet 9
Sheet 9
Adobe Patents Technology to Catch Where AI Misreads Plain-English Commands patent drawing, sheet 10
Sheet 10
Patent filing page

Watchlists this filing belongs to

All watchlists →