一作ACL 2026Findings· Findings of ACL
MEAV : Model Editing with Alignment Vectors for inference time LLM alignment in single and multidomain preference spectrum
Sadat Shahriar · Zheng Qi · Nikolaos Pappas · Srikanth Doss · Kishaloy Halder · Monica Sunkara · Manuel Mager · Yassine Benajiba
摘要
Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing training-time alignment methods require full re-training when a change is needed and infer...