Open-weight LLMs show no output bias on matched mortgage applications differing only by racially-associated names, yet retain and amplify demographic representations that steering interventions can causally activate to produce near-complete asymmetric decision reversals.
Inference-time intervention: Eliciting truthful answers from a language model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions
Open-weight LLMs show no output bias on matched mortgage applications differing only by racially-associated names, yet retain and amplify demographic representations that steering interventions can causally activate to produce near-complete asymmetric decision reversals.