Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Independent researcher, Lisbon, Portugal
2
0
4
Different LLMs interpret human values in social media texts variably, but targeted calibration can significantly enhance alignment with expert judgments.
LLMs, when used to annotate social media for human values, systematically overestimate "Openness to Change" compared to human experts, revealing a potential bias in automated value detection.