Skip to content
View vickywu97's full-sized avatar

Block or report vickywu97

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
vickywu97/README.md

Hi, I'm Vicky Wu 👋

Lawyer · Tax Adviser · Patent Attorney → building AI legal-product & compliance tooling that measures LLM quality.

I'm transitioning from legal / tax / patent practice into AI product and compliance roles. My open-source work shows I can do more than prompt an LLM — I can define and measure its quality on domain-grounded tasks.


🔬 Portfolio (pinned)

ProjectWhat it isHeadline signal
verified-chinese-law-kbModular, versioned corpus of 2,327 line-by-line verified Chinese statutory articles across 8 laws — attorney-signed, independently downloadable modules.Audit-ready legal ground truth for RAG / evaluation.
law-citation-benchOffline, stdlib-only benchmark quantifying LLM legal-citation accuracy (T1 grounding / T2 retrieval / T3 hallucination) over 500 deterministically generated questions.A one-line prompt fix recovered +97 points (Qwen T3 "未命中" 0.0000 → 0.9697).

▶ Landing page: law-citation-bench/index.html


📊 Why this matters

Mainstream legal LLMs hallucinate on citation. I built an offline benchmark that proves it, isolates the failure mode, and shows exactly how a prompt-level fix recovers accuracy — separating prompt-fixable failures from model hard-failures (e.g. GLM scoring 0 on retrieval). That is the core skill for an AI legal-product / compliance role: turn vague "the model is wrong" into a measured, fixable specification.


🧰 Skills

Legal AI · LLM evaluation & benchmarking · RAG data curation · Prompt engineering (failure-mode diagnosis) · Python (stdlib-only tooling) · Chinese statute & tax law · Patent law · Compliance & risk.


📝 Beyond code

I also write practitioner content on Chinese tax, compliance, and cross-border structuring (CRS, offshore trusts, tokenization/RWA, platform-tax audits). See the article index for thematic tagging across legal / tax / patent perspectives.


📫 Reach me


Background: licensed attorney (PRC), tax adviser, and patent attorney. Currently building portfolio evidence for AI legal-product / compliance roles.

Pinned Loading

  1. compliance-trianglecompliance-trianglePublic

    法律/税务/IP 三域合规助手 · 复用同一套校验引擎 · 对 AI 法条引注做 🟢🟡🔴 三层核验 · 离线零依赖

    Python

  2. legal-ai-watchlegal-ai-watchPublic

    Python 1

  3. legal-hallucination-benchlegal-hallucination-benchPublic

    中文法律引注幻觉基准 · 离线零依赖 · 2327 条专家核验法条 · 5 国产模型真实跑分

    Python

  4. verified-chinese-law-kbverified-chinese-law-kbPublic

    2,327 line-by-line verified Chinese statutory articles across 8 laws — modular, versioned, attorney-signed, independently downloadable. Audit-ready legal ground truth for RAG & LLM evaluation.

    Python