Do the thumbs up in prod affect LLM understanding

[sofiahd]

Hi all,

my team is currently testing the new patch 6 for NowAssist. Thumbs up/down seem to be training the LLM in Dev2.  Something I'm wondering though is if the training thumbs up/down in prod will affect LLM training also meaning that if users are not clear on procedures or dislike a procedures may affect 'the truth' of the LLM.

potentially is that something that can be kept for dev2 for training purposes and have thumbs up/down show in prod but only as feedback that don't affect LLM training?

[rpriyadarshy]

Hi

Thumbs Up & Down are part of feedback loop in terms of LLM response. How it goes in background its as below.

Have a look at This Table--> sys_gen_ai_log_metadata.

Data and Logs are too much encapsulated so not easy to decode . Have a look at table - SYS_GEN_AI_LOG_METADATA

Just tried Another Like - and 1 dislike in Chat Window and another entry appears for Both

Ane here are the entries for all the feedback.

2 like and 1 dislike 

Regards

RP