Task-Aware Spectral Pruning (TASP), a post-training framework that calibrates module-level spectral descriptors against measured task-specific ablation effects, closes grouped-query-attention and SwiGLU dependencies during sparse-mask construction, and routes each user turn to one compiled mask that remains fixed throu...
A scalar recalibration map fitted for an LLM judge on one task can fail when the task distribution changes, but the source-target accuracy gap is often treated as a proxy for that failure. We test what this gap can predict and what it can certify across thirteen judges, two generators, eight domains, and 1,176 predecla...
It is proved that common-mode error is not identifiable from internal judge scores alone and proposed a bounded two-anchor Bernstein certificate for finite-search error and regret.
This work formulate PRM stress testing as a quality-diversity search problem using MAP-Elites, retaining the most severe correctness-flipping edit in each behavior-space region while separating search coverage from exploit coverage, and characterize what such archives certify.
Ibne Farabi Shihab, Fariya Afrin· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
