Study on Guilty Bias
Legal judgment prediction models may retain a guilty verdict after a legally decisive condition has been altered such that the specified charge is no longer established. We study this guilty bias via selective repair over matched charge-established and charge-not-established cases, where the unsupported verdict should change while its supported counterpart remains stable.
We construct CAIL-MC, a legally reviewed dataset of 11,478 matched pairs covering 261 Chinese criminal charges.
Held-out activation interventions show that contrasts learned from correctly resolved pairs transfer to false-guilty cases, but target-reaching interventions can also damage matched supported-guilty decisions.
PROSE: Residual Geometry-Driven Safe Repair
Motivated by this observation, we introduce PROSE, which reconstructs case-specific targets from a training-derived residual geometry, aligns them with a local margin-descent signal, attenuates supported-guilty-sensitive components, and realizes bounded targets through a preservation-regularized low-rank parameter update.
Across Qwen3-8B and GLM4-9B, PROSE achieves stronger pairwise safe repair and evidence sensitivity, while preserving standard single-pass inference.