Here we summarize the discussion that took place after the presentation of papers discussing measurement of abundances from emission lines in H II regions. A cosmological test using 4He is harder than those using the other light elements due to the small dynamic range over which He/H varies for cosmologically interesting parameters. A precision of much better than 1% is needed. This precision challenges both observations and theory. Several of the major uncertainties were identified and methods of improving the accuracy were described.