A systematic comparison of ICL, LoRA fine-tuning, and activation steering for Big Five personality control, with new contrastive data and evaluation metrics, but with key claims contradicted by the reported experiments.
Evaluating feature steering: A case study in mitigating social biases
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects
A systematic comparison of ICL, LoRA fine-tuning, and activation steering for Big Five personality control, with new contrastive data and evaluation metrics, but with key claims contradicted by the reported experiments.