A Reality Check of Inference-Time Context Augmentation Methods
Tests inserting blank filler, repeated or rephrased sentences, and generated explanations at different points in a prompt. Tracks both corrected and newly broken answers across seven models and three datasets, showing why average accuracy alone can hide unreliable gains.
First public: · Added to this list: October 23, 2026
Explore this approach
Thinking tokens — Give a model extra tokens for computation, such as pauses, filler symbols, or learned planning tokens. These tokens need not spell out the solution.
Analysis and evaluation — Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.