3 papers
cs.AI2026
Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions
Jagdish Tripathy, Marcus Buckmann
Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representations. However, whether thes…
cs.CL2025
Revealing economic facts: LLMs know more than they say
Marcus Buckmann, Quynh Anh Nguyen, Edward Hill
We investigate whether the hidden states of large language models (LLMs) can be used to estimate and impute economic and financial statistics. Focusing on county-level (e.g. unempl…
cs.CL2024
Logistic Regression makes small LLMs strong and explainable "tens-of-shot" classifiers
Marcus Buckmann, Edward Hill
For simple classification tasks, we show that users can benefit from the advantages of using small, local, generative language models instead of large commercial models without a t…