一作ACL 2026Poster· Natural Language Processing
Improving the Distributional Alignment of LLM s using Supervision
Gauri Kambhatla · Sanjana Gautam · Angela Zhang · Alexander Liu · Ravi Srinivasan · Junyi Jessy Li · Matthew Lease
摘要
The ability to accurately align LLMs with diverse population groups on subjective questions would have great value. In this work, we show that adding simple supervision can more consistently improve the alignment of LLM-generated distributions with diverse population groups, as measured across th...