TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

research

Dynamic Modes Ranked the Tokens Behind a Decision

DMDIntel decomposes hidden-state trajectories before attributing a classifier's output to input tokens.

Published Updated Story ID: mp-2026-08-14-016
Read the complete editionStory JSON

Summary

DMDIntel decomposes hidden-state trajectories before attributing a classifier's output to input tokens.

Across three datasets and three model families, the authors report stronger ranked attributions than PCA, integrated gradients and SHAP. The comparisons evaluate the stated classification tasks; they do not make every language-model decision transparent.

Why it matters

DMDIntel decomposes hidden-state trajectories before attributing a classifier's output to input tokens.

Limits and context

  • The comparisons evaluate the stated classification tasks; they do not make every language-model decision transparent.

Key claims

  1. DMDIntel decomposes hidden-state trajectories before attributing a classifier's output to input tokens.

    Qualification: The comparisons evaluate the stated classification tasks; they do not make every language-model decision transparent.

    Evidence: source-2026-08-14-018

Sources

  1. arXiv preprint 2608.13048arXiv · primary research

Corrections

No corrections have been recorded for this story.

Dynamic Modes Ranked the Tokens Behind a Decision · The Machine Press