← all papers · overview

Faithsteer-bench: A Deployment-aligned Stress-testing Benchmark For Inference-time Steering

Abstract

Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce targeted behavioral changes. However, such conclusions are typically drawn under relatively relaxed evaluation settings that overlook deployment constraints, ca

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).