BestHub
Sign in
Wu Shixiong's Large Model Academy
Author

Wu Shixiong's Large Model Academy

We continuously share large‑model know‑how, helping you master core skills—LLM, RAG, fine‑tuning, deployment—from zero to job offer, tailored for career‑switchers, autumn recruiters, and those seeking stable large‑model positions.

107
Articles
0
Likes
33
Views
0
Comments
Recent Articles

Latest from Wu Shixiong's Large Model Academy

100 recent articles max
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 31, 2026 · Information Security

Securing LLM Code Interpreter: Sandbox Strategies and Real‑World Pitfalls

This article examines why RAG systems need a Code Interpreter, explains the dangers of executing LLM‑generated code with exec(), and presents three sandbox designs—restricted exec, Docker containers, and E2B cloud sandboxes—along with whitelist/blacklist rules, an eight‑step execution flow, and practical lessons learned from production deployment.

DockerLLMPython
0 likes · 26 min read
Securing LLM Code Interpreter: Sandbox Strategies and Real‑World Pitfalls
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 30, 2026 · Operations

Mastering RAG Post‑Launch: A Closed‑Loop Badcase Management Blueprint

This article explains how to establish a six‑step closed‑loop workflow for operating RAG‑based question‑answer systems in insurance, covering badcase collection via three channels, four‑type classification, automated scripts, regression testing, gray‑scale rollout, and real‑world metrics that boosted answer accuracy from 76 % to 89 %.

Badcase ManagementInsurance AILLM
0 likes · 20 min read
Mastering RAG Post‑Launch: A Closed‑Loop Badcase Management Blueprint
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 29, 2026 · Artificial Intelligence

Mastering RAG Prompt Engineering: Prevent Hallucinations and Boost Accuracy

This article dissects the unique challenges of RAG prompting, presents a systematic System/User Prompt design with strong constraints and citation requirements, compares constraint strengths with quantitative hallucination rates, and offers long‑context compression strategies and rigorous testing methods to ensure reliable LLM answers.

Context CompressionLLMRAG
0 likes · 19 min read
Mastering RAG Prompt Engineering: Prevent Hallucinations and Boost Accuracy
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 28, 2026 · Artificial Intelligence

Mastering Multi‑Agent Systems: Design, Parallel Execution, and Interview Strategies

This article dissects the shortcomings of single‑agent LLM pipelines, introduces the Supervisor‑based Multi‑Agent architecture with LangGraph, demonstrates parallel task execution, robust error handling, and result merging, and provides concrete interview guidance backed by real performance data.

AI ArchitectureError HandlingLLM
0 likes · 19 min read
Mastering Multi‑Agent Systems: Design, Parallel Execution, and Interview Strategies
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 27, 2026 · Artificial Intelligence

Securing RAG Systems: A Three‑Layer Permission Framework for Banking AI

This article explains why vector databases lack row‑level security, presents a three‑layer permission architecture—including JWT authentication, Milvus metadata or partition filtering, and post‑retrieval validation—covers document security levels, PostgreSQL RLS, audit logging, caching strategies, and offers interview‑ready talking points.

JWTMilvusPermission Management
0 likes · 18 min read
Securing RAG Systems: A Three‑Layer Permission Framework for Banking AI
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 26, 2026 · Artificial Intelligence

Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Gains

This article explains why combining BM25 with dense vector search using Reciprocal Rank Fusion (RRF) improves recall for both exact‑term and semantic queries in a financial‑insurance document corpus, details the underlying algorithms, parameter choices such as k=60, provides Python implementations, and shows measurable performance gains in production.

BM25FAISSHybrid Retrieval
0 likes · 28 min read
Why Hybrid Retrieval Beats Pure Vector Search: BM25, RRF, and Real‑World Gains
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 22, 2026 · Artificial Intelligence

How to Overcome MinerU’s Top 9 Limitations for Reliable Document Parsing

This article examines MinerU’s strengths and nine critical shortcomings—such as reading order errors, split tables, merged cells, OCR misrecognition, formula handling, heading hierarchy loss, output inconsistency, hardware limits, and licensing issues—and provides concrete improvement strategies and interview‑ready talking points for engineers.

Document ParsingInterview TipsMinerU
0 likes · 12 min read
How to Overcome MinerU’s Top 9 Limitations for Reliable Document Parsing
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 21, 2026 · Artificial Intelligence

Step‑by‑Step Guide to Implementing a Hybrid Retrieval Function with RRF Fusion

This article breaks down the end‑to‑end retrieval function used in a RAG system, detailing each of the five stages—from request construction, hybrid vector + BM25 search, RRF fusion, cross‑encoder reranking, to threshold filtering—and provides concrete Python code, parameter choices, and performance insights.

Cross-EncoderElasticsearchHybrid Retrieval
0 likes · 13 min read
Step‑by‑Step Guide to Implementing a Hybrid Retrieval Function with RRF Fusion
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Mar 20, 2026 · Artificial Intelligence

Mastering MinerU: Overcoming Its Top 9 Limitations for Reliable Document Parsing

This article examines MinerU's strengths and nine critical shortcomings—such as layout order errors, cross‑page table splits, merged‑cell failures, OCR misrecognition, and licensing issues—and provides concrete improvement strategies, interview‑ready resume bullets, and practical response frameworks for engineers.

LLMLayout AnalysisMinerU
0 likes · 13 min read
Mastering MinerU: Overcoming Its Top 9 Limitations for Reliable Document Parsing