Evaluations without human blind evaluation

[ADiko1997]

Hi, have you evaluated the model using only GPT3.5/Claude without HBR? This is important for the research community to compare against your work.

[Espere-1119-Song]

Sure, you can refer to Table K10 and Table K11 in the Appendix of our paper

[ADiko1997]

Thank you very much for your reply. Best regards

…

On Tue, 3 Sept 2024, 17:46 EnxinSong, ***@***.***> wrote: Sure, you can refer to Table K10 and Table K11 in the Appendix of our paper — Reply to this email directly, view it on GitHub <#78 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AL3UZJAO3MQBGOPP7BE7ODDZUXDT7AVCNFSM6AAAAABNRVNPWKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDGMRWG4YTSMRZGI> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[lan-lw]

Hi can you provide the moviechat+ model using GPT3.5/Claude without HBR ? I didn't find the results in moviechat+ paper.