Understanding the Effects of RLHF on LLM Generalisation and Diversity — mentioned by f0e4c2f7

Mon, 12 Aug 2024 01:27:10 GMT

There have been some papers showing that RLHF makes models more palletable to use but reduces performance on evals and in other various ways. I couldn't find the one I was looking for but this is one of them. https://arxiv.org/abs/2310.06452 Edit: This tweet also has a screenshot showing degraded evals from RLHF from base model. https://x.com/KevinAFischer/status/1638706111443513346?t=0wK...

Paper and discussion history. A mention is not an endorsement.

Understanding the Effects of RLHF on LLM Generalisation and Diversity — mentioned by cosmojg

Thu, 07 Dec 2023 05:33:29 GMT

What was the point of moving away from the base model? I can't stop asking this question. Conversational formatting is achievable with careful prompting and a bit of good old-fashioned heuristic post-processing, and it was easier to achieve consistent results before RLHF took off. Now we still have to do a bunch of prompt hacking to get the results we want[1], but it's more complicated and the performance of the model has degraded significantly[2]. All the cargo culting toward agentic chatbots and away from language prediction engines might please the marketing and investor relations…

Paper and discussion history. A mention is not an endorsement.

Understanding the Effects of RLHF on LLM Generalisation and Diversity · HackerPapers discussions

Understanding the Effects of RLHF on LLM Generalisation and Diversity — mentioned by f0e4c2f7

Understanding the Effects of RLHF on LLM Generalisation and Diversity — mentioned by cosmojg