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 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 →
LLM 中等

What is autoregressive generation in the context of LLMs?

作答 →
LLM 中等

What is the purpose of temperature in LLM inference, and how does it affect the output?

作答 →
LLM 中等

Explain how self-attention is computed in the Transformer model step by step

作答 →
LLM 中等

Explain the trade-offs in using a large vocabulary in LLMs

作答 →
LLM 中等

Explain why subword tokenization is preferred over word-level tokenization in the Transformer model

作答 →
LLM 中等

What are the possible options to speed up LLM fine-tuning?

作答 →
LLM 中等

What is gradient accumulation, and how does it help with fine-tuning large models?

作答 →
LLM 中等

Explain different preference alignment methods and their trade-offs

作答 →
LLM 中等

How do LLMs handle out-of-vocabulary (OOV) words?

作答 →