面试题库

全部 Django Elasticsearch FastAPI Flask Function Call JVM Java IO Java 后端 Java 基础 Java 并发 Java 新特性 Java 集合 JavaWeb Kafka LLM LangChain LangGraph MongoDB MyBatis MySQL Netty Nginx Python RAG RabbitMQ Redis RocketMQ Spring Spring AI SpringBoot SpringCloud SpringMVC ZooKeeper 分布式 后端技术 大厂面经 大数据 微服务 提示词工程 操作系统 数据库 数据结构 智能体 海康威视2026秋季社招专项 消息队列 监控运维 算法 系统设计 缓存 计算机基础 计算机网络 设计模式 面试题 高可用 高并发
LLM 中等

What is the purpose of the decoder in a transformer model?

作答 →
LLM 中等

What is the purpose of the encoder in a transformer model?

作答 →
LLM 中等

How are the outputs of multiple heads combined and projected back in the multi-head attention in the Transformer model?

作答 →
LLM 中等

Why does the Transformer model use multiple self-attention heads instead of a single self-attention head?

作答 →
LLM 中等

What is the purpose of scaling in the self-attention mechanism in the Transformer model?

作答 →
LLM 中等

What is the difference between zero-shot and few-shot prompting?

作答 →
LLM 中等

What is prompt engineering, and why is it important for LLMs?

作答 →
LLM 中等

Explain the trade-offs in using CoT prompting

作答 →
LLM 中等

Explain the key ingredient behind the effectiveness of the LoRA technique

作答 →
LLM 中等

What is LoRA, and how does it work at a high level?

作答 →
LLM 中等

When should you prefer task-specific fine-tuning over prompt engineering?

作答 →
LLM 中等

Explain the strengths and limitations of autoregressive text generation in LLMs

作答 →