“That seems to be similar to this approach, at least at a cursory level: Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback https://arxiv.org/abs/2302.12813 The “facts” being derived not from Wikipedia but rather the rules of the fictional world.”
Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e.g., task-oriented dialog and question answering. However, applying LLMs to real-world, mission-critical applications remains challenging mainly due to their tendency to generate hallucinations and their inability to use external knowledge. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules. Our system makes the LLM generate responses grounded in external knowledge, e.g., stored in task-specific databases. It also iteratively revises LLM prompts to improve model responses using feedback generated by utility functions, e.g., the factuality score of a LLM-generated response. The effectiveness of LLM-Augmenter is empirically validated on two types of scenarios, task-oriented dialog and open-domain question answering. LLM-Augmenter significantly reduces ChatGPT's hallucinations without sacrificing the fluency and informativeness of its responses. We make the source code and models publicly available.
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- Improving Large Language Models with External Knowledge and Automated Feedback ↗georgehill · 2023-02-27 · 1 分
- Improving large language models with external knowledge and automated feedback ↗PaulHoule · 2023-02-28 · 4 分
- Check Your Facts and Try Again: Improving LLMs with External Knowledge ↗tobr · 2023-04-30 · 1 分