作者位次 #5/7ACL 2026Poster· Natural Language Processing
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing
Michael Lan · Narmeen Fatimah Oozeer · Chaithanya Bandi · Philip Quirke · Austin Meek · Fazl Barez · Amir Abdullah
摘要
While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments. As such, many of its findings remain underutilized in safety-critical applications such as medical AI and autonomous sy...