Get the newsletter
Microsoft · AI / ML · Filed Jun 24, 2025 · USPTO published Nov 19, 2026 · This week's release

Microsoft Files Patent for Fact-Checking AI Summaries Against the Original Documents

AI summaries of long documents get built in layers, and every layer can add a mistake. Microsoft's patent application describes a checker that walks back through those layers and shows you the exact sentence behind each claim.

A chatbot window tracing an AI summary back through multi-level source chapters to prove its answer is accurate. Drawing from patent filing US 2026/0368567 A1.
A chatbot window tracing an AI summary back through multi-level source chapters to prove its answer is accurate.All 11 drawings ↓
Publication number
US 2026/0368567 A1(US20260368567A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
Jun 24, 2025 · Nov 19, 2026
Inventors
Dasha METROPOLITANSKY
Status when we published
Waiting for an examiner
Document
20 claims
US classification
706/12
Parent application
Claims priority from a provisional application 63806533 (filed May 15, 2025)

What Microsoft's AI fact-check trail does

Ever asked an AI to summarize a long report and then wondered whether any single line was actually in there? With very long material, the AI often works in layers: it summarizes chunks, then summarizes those summaries, then summarizes again. Each layer is another chance for a mistake to slip in.

Microsoft's patent application describes a checker that takes the final summary, breaks it into individual statements, and hunts for the evidence behind each one. It walks backward through the layers until it lands on the exact sentence in the original text, or finds the layer where things went off the rails.

The filing's example is a chatbot asked whether a biography shows a character loving graphs and logic. You can ask for a trail and see that one supporting line was actually a joke: "Just kidding. My true passion is graphs." The claim gets flagged as not fully supported.

From the filing · CLAIM 1
modeling a multi-stage generative pipeline based upon original source documents as a Directed Acyclic Graph (DAG) …

Translation: The system maps out how an AI creates text by turning source documents into a connected web of steps.

How the checker walks back through summaries

The patent models a multi-step AI process as a directed acyclic graph (DAG), which is a map of boxes and arrows where the arrows only point one way and never loop back. The original documents are the starting boxes (called root nodes, meaning boxes with no arrows coming in). Every AI-written summary or answer is another box, and the final answer is the last box, called the terminal node.

The checker splits that final box into individual claims, meaning single statements that can be verified. For each claim it repeats three steps:

  • Gather evidence: text from the boxes feeding the final answer is cut into chunks, and every sentence gets a unique ID. The AI picks the IDs of sentences that strongly support or contradict the claim. Those IDs are checked against the real ones, so a made-up sentence gets thrown out.
  • Give a verdict: the AI reads short summaries of that evidence and answers "fully supported," "not fully supported," or "inconclusive."
  • Backtrack: if the claim holds up, the process steps one layer down to the boxes that fed the ones with evidence, then repeats until it reaches the original text.

Each claim ends with verdicts and an evidence trail: the exact sentences, which box each came from, and the summaries made along the way. If a claim fails, the in-between verdicts point to the layer where the unsupported content likely appeared. The filing says only boxes that contributed evidence get checked further, which cuts the workload. A chat-style screen can show the graph with the supporting path circled next to the trail.

From the filing · THE ABSTRACT
… attempting to identify a provenance trace from an individual claim through individual intermediate nodes to an individual root node …

Translation: It checks if an AI statement is true by tracing it backward through every step of the drafting process to the source material.

Why summaries of long documents need receipts

If you use AI to summarize long documents, the practical question is always whether you can trust a given line. A trail that leads to the exact sentence turns "take my word for it" into something you can click and check. The filing lists a doctor reading medical literature, a lawyer summarizing past cases and a customer service agent working from policy documents as places where this matters.

It also helps the people building these tools. The filing says that when a claim fails, you can see which layer added the unsupported content, which tells builders where to fix things. It describes the checker running on a phone, a tablet or a cloud server, and mentions Microsoft's own GraphRAG as one layered process it could check. The filing also reports that it beat the other checking methods the authors tested on book summaries and news questions.

That makes this Microsoft's 31st filing we've tracked since July in the AI safety guardrails race, adding to one catching filtered images and one screening AI assistant traffic.

Source: US 2026/0368567 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 Microsoft 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 · 11 sheets

11 drawing sheets from US 2026/0368567 A1 · click any drawing to enlarge

Asking an AI chatbot a question about a long book, drawing sheet 1 from US 2026/0368567 A1
Sheet 1 Asking an AI chatbot a question about a long book
An AI chatbot answering without showing any proof, drawing sheet 2 from US 2026/0368567 A1
Sheet 2 An AI chatbot answering without showing any proof
Asking the chatbot to verify where its answer came from, drawing sheet 3 from US 2026/0368567 A1
Sheet 3 Asking the chatbot to verify where its answer came from
Tracing an AI claim back to the source text, drawing sheet 4 from US 2026/0368567 A1
Sheet 4 Tracing an AI claim back to the source text
Catching a false AI claim against the original book, drawing sheet 5 from US 2026/0368567 A1
Sheet 5 Catching a false AI claim against the original book
How the tool tests claims and gathers evidence, drawing sheet 6 from US 2026/0368567 A1
Sheet 6 How the tool tests claims and gathers evidence
Test scores comparing the fact checking method against rivals, drawing sheet 7 from US 2026/0368567 A1
Sheet 7 Test scores comparing the fact checking method against rivals
Data showing higher accuracy across different test conditions, drawing sheet 8 from US 2026/0368567 A1
Sheet 8 Data showing higher accuracy across different test conditions
Show the other 3 sheets
Connecting phones and tablets to cloud servers for verification checks, drawing sheet 9 from US 2026/0368567 A1
Sheet 9 Connecting phones and tablets to cloud servers for verification checks
The AI model that turns source text into summaries, drawing sheet 10 from US 2026/0368567 A1
Sheet 10 The AI model that turns source text into summaries
Tracing generated claims back to the original source text, drawing sheet 11 from US 2026/0368567 A1
Sheet 11 Tracing generated claims back to the original source text
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.