自我 RAG 和反思检索测验

当您参加测验时，就会出现答案和解释。

1. 与针对每个输入都进行检索的基准方法相比，Self-RAG 学习到了什么样的自适应决策？
   • Which operating system to install for every query
   • Whether retrieval is needed, including decisions as generation progresses
   • How to permanently remove all document sources
   • How to prove every generated statement without inspecting evidence
2. Self-RAG 中的“反射令牌”是什么？
   • 文档的加密密钥
   • 用户登录凭据
   • 检索到的文件上的时间戳
   • 模型发出的特殊控制令牌，用于判断相关性、支持性和有用性
3. Self-RAG 的 IsSupported 反思标记预测的是什么？
   • Whether the model's hardware has enough disk space
   • Whether a support ticket has been paid
   • Whether a generated segment is supported by the retrieved evidence
   • Whether every source claim is independently proven true
4. 通常如何训练 Self-RAG 模型来生成反射标记？
   • 对标有反射标记的数据进行监督学习，通常从更强大的模型中提取
   • 纯无监督聚类
   • 通过手动编码规则而无需学习
   • 仅通过人类点击进行强化学习
5. 对每个段落发出“IsRelevant”批评有什么好处？
   • 它加快了网络连接速度
   • 它压缩文档存储
   • 它改变了模型的标记器
   • 它过滤掉检索到的实际上对查询没有帮助的段落
6. How can reflection-token scores affect Self-RAG inference without a new training run?
   • Every query must update all model parameters
   • Weighted critique scores can be combined with generation likelihood during segment-level candidate search
   • The critique scores must replace all source text with random tokens
   • Changing a score weight guarantees all factual errors disappear
7. What should an evaluator infer from a high Self-RAG IsSupported probability alone?
   • The model predicts support, which still needs checking against the actual evidence
   • The answer has been independently verified as true
   • No source passage needs to be read
   • Every external document is guaranteed accurate
8. At what granularity can Self-RAG adapt retrieval while developing a response?
   • Only when the operating system restarts
   • Only after the final answer has been published
   • As generated segments progress, rather than only one fixed retrieval at the beginning
   • Only by changing the tokenizer's vocabulary permanently