Concepthidden state decoding
Hidden State Decoding
An interpretability technique that does not rely on model output text but instead directly reads the model's internal neural activations (hidden states), using these representations to infer the decisions or classifications the model is inclined to make.
Timeline (last 90 days)
Oct 13
The study uses counterfactual auditing to test the chain-of-thought faithfulness of legal AI: while keeping the case facts fixed and unchanged, it replaces the legal basis cited by the model and decodes the decision tendency from the model's hidden states, in order to judge whether the decision truly depends on the cited basis.
Unverified50%