按年被提到
20232023 · 1 次2026
大模型与语言模型›大模型预训练与缩放·arXiv:2310.06452 · cs.LG

Understanding the Effects of RLHF on LLM Generalisation and Diversity

Robert Kirk, Ishita Mediratta, Christoforos Nalmpantis, Jelena Luketina, Eric Hambro, Edward Grefenstette, Roberta Raileanu · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-12-07 · 最近 2024-08-12
2不同的人
2活跃月份
2讨论串
82被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large language models (LLMs) fine-tuned with reinforcement learning from human feedback (RLHF) have been used in some of the most widely deployed AI models to date, such as OpenAI's ChatGPT or Anthropic's Claude. While there has been significant work developing these methods, our understanding of the benefits and downsides of each stage in RLHF is still limited. To fill this gap, we present an extensive analysis of how each stage of the process (i.e. supervised fine-tuning (SFT), reward modelling, and RLHF) affects two key properties: out-of-distribution (OOD) generalisation and output diversity. OOD generalisation is crucial given the wide range of real-world scenarios in which these models are being used, while output diversity refers to the model's ability to generate varied outputs and is important for a variety of use cases. We perform our analysis across two base models on both summarisation and instruction following tasks, the latter being highly relevant for current LLM use cases. We find that RLHF generalises better than SFT to new inputs, particularly as the distribution shift between train and test becomes larger. However, RLHF significantly reduces output diversity compared to SFT across a variety of measures, implying a tradeoff in current LLM fine-tuning methods between generalisation and diversity. Our results provide guidance on which fine-tuning method should be used depending on the application, and show that more research is needed to improve the tradeoff between generalisation and diversity.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论cosmojg · 2023-12

“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 wan…”

Anthropic Claude performance depends heavily on prompt style原评论 ↗
评论f0e4c2f7 · 2024-08

“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/KevinAF…”

Ask HN: Has degradation in the quality of ChatGPT and Claude been proven?原评论 ↗