“> LLMs aren't like that, they don't really know what they do know. They actually do. The information is saved there, you just need to ask explicitly, because the usual response doesn't expose it. (But likely can be fine tuned to do that) https://ar5iv.labs.arxiv.org/html/2308.16175 Also the original claim was that they're not capable of responding with …”
Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness
We introduce BSDetector, a method for detecting bad and speculative answers from a pretrained Large Language Model by estimating a numeric confidence score for any output it generated. Our uncertainty quantification technique works for any LLM accessible only via a black-box API, whose training data remains unknown. By expending a bit of extra computation, users of any LLM API can now get the same response as they would ordinarily, as well as a confidence estimate that cautions when not to trust this response. Experiments on both closed and open-form Question-Answer benchmarks reveal that BSDetector more accurately identifies incorrect LLM responses than alternative uncertainty estimation procedures (for both GPT-3 and ChatGPT). By sampling multiple responses from the LLM and considering the one with the highest confidence score, we can additionally obtain more accurate responses from the same LLM, without any extra training steps. In applications involving automated evaluation with LLMs, accounting for our confidence scores leads to more reliable evaluation in both human-in-the-loop and fully-automated settings (across both GPT 3.5 and 4).
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“LLMs encode their certainty enough to output it again. They don't need to be specifically trained for this. https://ar5iv.labs.arxiv.org/html/2308.16175”
- Quantifying Uncertainty in LM Answers via Intrinsic and Extrinsic Assessment ↗PaulHoule · 2023-09-05 · 1 分
- Quantifying Uncertainty in Answers from LLM and Enhancing Their Trustworthiness ↗handfuloflight · 2024-08-28 · 1 分