Huseyin Atahan Inan

icon indicating a website link https://www.microsoft.com/en-us/research/people/huinan/

icon company Microsoft icon location Redmond, US icon location I am a senior researcher in the Privacy in AI group at MSR. I am working in the field of privacy-preserving ML with a particular focus on NLP applications.

Results 2 comments of Huseyin Atahan Inan

How to generate reference answers in MT-Bench?

I am also confused about this. I might be missing something obvious but it seems to me that the reference answers are from here: https://github.com/lm-sys/FastChat/blob/main/fastchat/llm_judge/data/mt_bench/reference_answer/gpt-4.jsonl But for some questions, answers...

How to generate reference answers in MT-Bench?

Hi @infwinston, many thanks for the clarification, I understand. Just an interesting note that when I downloaded pre-generated data via `python3 download_mt_bench_pregenerated.py` I see that actually gpt-4 generates more correct...