HarmCap: State-Aware Consequence Control for Retrieval-Conditioned Tabular Prediction

Retrieval-conditioned tabular models use neighboring examples or in-context demonstrations to adapt predictions at inference time, but a strong retrieval mechanism does not by itself control how much one realized update may deteriorate an individual prediction. We introduce HarmCap, a post-retrieval controller that treats the retrieval-conditioned output as a proposal and selects the largest query-specific step along its realized logit-space direction whose worst label-wise cross-entropy increase stays within a prescribed budget. The admissible step depends on the full predictive state, making scalar confidence insufficient for exact multiclass control. Across public tabular benchmarks and multiple retrieval-conditioned interfaces, HarmCap satisfies the prescribed pointwise contract while retaining more of the proposed update than a state-agnostic exact-safe envelope. Protocol-aligned TabR experiments further recover the predictive behavior reported in the original work before applying HarmCap to matched same-checkpoint retrieval updates. The experiments also show that admissibility and predictive utility are distinct objectives, supporting consequence control as a separate inference-time component of retrieval-conditioned prediction.