AI Output Error Highlighting Using Token-Level Confidence Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing AI systems do not effectively inform users about the likelihood of errors in their output data, making it difficult for users to recognize the degree of possibility that elements in the output include errors.

Innovation Solution

An information processing system that includes a processor to acquire input and output data generated by AI, and provides error possibility information indicating the likelihood of errors in the output data, attaching this information to specific elements within the output, such as text data, using a large language model to analyze the contribution of knowledge neurons in predicting subsequent elements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If AI generates output data in response to input data, then productivity and automation are improved, but the reliability and accuracy of the output data deteriorate due to potential errors

Engineering Contradiction:
ImproveAI output generation speedVSAvoidoutput data accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system implements feedback by analyzing the generated output data through the processor to determine error possibility, then providing this information back to the user. This allows the system to self-evaluate its output quality and inform users about potential errors, resolving the contradiction between high-speed AI generation and reliable output.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If error possibility information is provided for all elements in output data, then measurement precision and reliability are improved, but device complexity and information processing load increase

Engineering Contradiction:
Improveerror detection precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies local quality by providing error possibility information selectively rather than uniformly across all elements. The processor determines error possibility for each element based on its specific characteristics and the AI model's confidence, allowing detailed precision where needed while maintaining simplicity where not required.

Inventive Principle:
Principle #3Local quality

3Loss of information

If error possibility information is attached to specific elements in output data, then information completeness is improved, but ease of operation and user comprehension become more difficult

Engineering Contradiction:
Improveerror information completenessVSAvoiduser comprehension ease
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system segments error possibility information by attaching it to specific elements within the output data rather than providing a single overall error rating. This segmentation allows users to comprehend the output element-by-element, maintaining ease of operation while providing complete error information where relevant.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4703963A1Information processing system and program
Publication Date: 2026.03.04 FUJIFILM BUSINESS INNOVATION CORP
  • EP4703963A1 patent drawingFigure 1
  • EP4703963A1 patent drawingFigure 2
  • EP4703963A1 patent drawingFigure 3

AI summary

An information processing system includes a processor configured to: acquire input data; acquire output data generated by artificial intelligence in response to the input data; and output the output data and error possibility information indicating a degree of possibility that an element of multiple elements in the output data includes an error by the artificial intelligence.