> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bono.network/llms.txt
> Use this file to discover all available pages before exploring further.
# GitLaw Legal Research
> Real-time legal research that solves AI's citation hallucination problem
## The Problem with AI Legal Research
Before explaining what GitLaw does, you need to understand why traditional AI approaches fail for legal research - and why this matters for your practice.
### The Citation Hallucination Problem
Standard AI models (like ChatGPT, Claude, or Gemini) have a serious problem: **they make up citations**. They'll confidently cite cases that don't exist, misquote holdings, or attribute statements to the wrong court. This isn't a bug - it's fundamental to how these systems work.
**Real examples of AI hallucination:**
* Citing "Smith v. Jones, 542 F.3d 1234 (9th Cir. 2018)" - a case that doesn't exist
* Quoting a statute with incorrect section numbers
* Attributing a holding to the Supreme Court when it came from a district court
* Inventing law review articles with plausible-sounding authors
**This is not theoretical.** Lawyers have been sanctioned for filing briefs with AI-generated fake citations. In 2023, a federal judge imposed sanctions after counsel submitted a brief citing six non-existent cases, all generated by ChatGPT.
### Why This Happens: How AI Actually Works
To understand the problem, you need to understand two concepts:
**1. Training Data Cutoff**
AI models are trained on data up to a certain date. After that, they know nothing. A model trained through 2023 has no knowledge of:
* Cases decided in 2024
* Statutory amendments
* New regulations
* Recent court interpretations
When asked about recent developments, the AI either says "I don't know" or - more dangerously - makes something up that sounds plausible.
**2. The Single-Source Problem (Hapax Legomenon)**
AI models learn from their training data. When a topic appears only once or a few times in that data, the AI treats that source as authoritative - even if it's wrong.
This is catastrophic for legal research:
* **OCR errors in scanned documents** - A case citation scanned with an error (e.g., "542 F.3d" instead of "524 F.3d") becomes "truth" to the AI
* **Transcription mistakes** - A single court opinion with a typo in a party name propagates as fact
* **Outdated sources** - If the only training source for a niche legal topic is from 2015, the AI presents 2015 law as current
* **Regional law** - For smaller jurisdictions or specialized courts, there may be only one or two training sources, and any errors in them become gospel
**This problem is dramatically worse for non-English jurisdictions.** English legal content dominates AI training data. For German, French, Portuguese, or Japanese law, training sources are scarcer. If the one Portuguese case discussing a particular doctrine was OCR'd with errors, the AI will confidently cite that error forever.
The AI doesn't know it's wrong. It presents these errors with the same confidence as well-established legal principles.
**3. Weak Agentic Design (AI That Doesn't Actually Search)**
Many "AI research" tools have a fundamental design flaw: the AI can choose whether to search or just answer from memory. Without proper safeguards, the AI often:
* **Skips the search entirely** - It "thinks" it knows the answer and responds from training data
* **Searches superficially** - Does one quick search, finds nothing useful, and falls back to hallucination
* **Mixes sources** - Combines real search results with made-up information to fill gaps
This is why you see AI tools with "web search" enabled still producing fake citations. The AI decided it already knew the answer, or the search didn't return what it expected, so it fabricated the rest.
**You have no way to know when this happens.** The AI presents hallucinated content with the same confidence as researched content. There's no indicator saying "I made this up because my search failed."
**4. RAG (Retrieval-Augmented Generation)**
To fix the knowledge cutoff problem, many AI systems use "RAG" - they search a database, retrieve relevant documents, and feed them to the AI as context. This sounds good but has serious limitations:
| RAG Limitation | Why It Matters for Legal Research |
| --------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Surface-level matching** | RAG finds documents with similar words, not similar legal concepts. A search for "breach of fiduciary duty" might miss cases using "violation of duty of loyalty" |
| **Context window limits** | RAG can only feed so much text to the AI. Complex legal issues requiring synthesis of multiple long opinions get truncated |
| **No legal reasoning** | RAG retrieves text but doesn't understand legal hierarchy, binding vs. persuasive authority, or how to apply precedent |
| **Garbage in, garbage out** | If the underlying database is incomplete or the search misses relevant cases, the AI confidently answers based on incomplete information |
### The Multi-Jurisdictional Nightmare
These problems compound dramatically for international or multi-jurisdictional research:
**Non-English Jurisdictions**
* Most AI training data is English-language
* Case law from Germany, France, Brazil, Japan is underrepresented
* Legal terminology doesn't translate directly
* Citation formats vary by country
* AI hallucinates non-English citations at even higher rates
**Complex Comparative Questions**
* "Compare GDPR enforcement with CCPA" requires deep knowledge of both regimes
* Surface-level search returns overview articles, not authoritative sources
* AI may conflate different legal systems
* Nuances between common law and civil law traditions get lost
***
## How GitLaw Solves These Problems
GitLaw is Arbiter's solution to AI legal research failures. It works fundamentally differently from RAG-based systems.
### Real-Time Web Search, Not Static Databases
Instead of searching a pre-built database (which is always out of date), GitLaw searches the live internet for legal content when you ask a question. This means:
* **No knowledge cutoff** - Finds cases decided yesterday
* **Current regulations** - Gets the latest version of statutes
* **Recent commentary** - Finds new law review articles and analysis
### Contextual Retrieval, Not Keyword Matching
GitLaw Premium doesn't just match keywords. It understands what you're asking and retrieves content contextually:
| Approach | How It Works | Result |
| ---------------------------------- | --------------------------------------------------------------------------------------- | -------------------------------------------------------- |
| **Basic Search** | Matches keywords like "non-compete California" | Returns anything mentioning those words |
| **Semantic Search (Fast Mode)** | Finds conceptually similar content | Better, but still surface-level |
| **Contextual Retrieval (Premium)** | Understands legal question, searches in native terminology, analyzes results in context | Finds relevant authority even with different terminology |
### Native Language Legal Search
For non-English jurisdictions, GitLaw searches in the native legal language:
* **German**: Searches "BGB § 823 Schadensersatzpflicht" not just "German tort law"
* **French**: Searches "responsabilité délictuelle Code civil" not "French liability"
* **Spanish**: Searches "incumplimiento contractual Código Civil" not "Spanish breach of contract"
* **Portuguese**: Searches "Lei Geral de Proteção de Dados" not "Brazilian privacy law"
This dramatically improves results for international research.
### Citation Verification
Unlike standard AI that generates citations from its imagination, GitLaw:
1. Searches for actual sources
2. Extracts real citations from those sources
3. Provides links to verify
4. Indicates confidence level for each citation
You can see exactly where each citation came from and click through to verify.
***
## Research Modes
Arbiter offers two GitLaw modes:
**Semantic Search**
* Finds conceptually similar content
* Good for preliminary research
* Faster response times
* Lower cost (\~40 tokens)
* Best for: Quick lookups, common legal questions, initial research
**Contextual Retrieval**
* Deep AI-powered analysis of results
* Searches in native legal terminology
* Better citation extraction
* Higher quality synthesis
* Higher cost (\~200 tokens)
* Best for: Final research, complex questions, non-English jurisdictions, court filings
**When to use Premium:** Multi-jurisdictional questions, non-English law, anything you'll rely on for client advice or court filings. The extra cost is worth it for accuracy.
***
## Using GitLaw
### Enabling Web Research
In the chat input bar, click the globe icon to enable web research
Click the dropdown to select Fast Search or GitLaw Premium
Type your legal question with as much context as possible
See real-time indicators as Arbiter searches and analyzes sources
### What Happens Behind the Scenes
When GitLaw runs:
1. **Query Generation** - AI formulates optimal search terms (including native language terms for international questions)
2. **Multi-Source Search** - Searches across legal databases, court websites, regulatory sites, and authoritative sources
3. **Result Analysis** - AI reads and analyzes each result for relevance
4. **Citation Extraction** - Identifies and extracts actual citations from sources
5. **Synthesis** - Composes answer with proper attribution to sources
### Research Results Card
When research completes, you'll see an expandable card showing:
* **Sources Found** - How many sources were retrieved
* **Queries Used** - What search terms were used
* **Citations** - All legal citations extracted with links
* **Confidence Levels** - How reliable each citation is
***
## Citation Quality Indicators
GitLaw indicates how confident it is in each citation:
| Indicator | Meaning | Action |
| --------------------- | ------------------------------------------ | ---------------------------- |
| **Verified** | Citation confirmed against official source | Safe to use |
| **High Confidence** | Strong match to authoritative source | Should be reliable |
| **Medium Confidence** | Good match, source accessible | Recommend quick verification |
| **Low Confidence** | May need manual verification | Verify before using |
**Always verify critical citations.** GitLaw is far more accurate than standard AI, but for court filings and formal opinions, verify key authorities through official sources (Westlaw, LexisNexis, official court websites).
***
## Best Questions for GitLaw
"What are the current SEC requirements for SPAC disclosures after the 2024 rule changes?"
GitLaw finds the latest regulations and guidance - something a model with a knowledge cutoff cannot do.
"What is the standard for piercing the corporate veil under Delaware law?"
GitLaw searches Delaware cases and statutes specifically, not generic corporate law principles.
"What are the employee termination notice requirements under German law for employees with more than 10 years of service?"
GitLaw searches German legal sources in German, finding BGB provisions and relevant case law.
"Find recent Delaware Chancery Court cases on earn-out disputes from 2023-2024"
GitLaw searches for actual recent opinions, not hallucinated citations.
"What are the GDPR requirements for data breach notification timelines?"
GitLaw finds the specific regulatory provisions and recent guidance from EU authorities.
"Compare enforcement mechanisms for non-compete agreements in California, Texas, and New York"
GitLaw researches each jurisdiction separately and synthesizes a comparison.
***
## When GitLaw Runs Automatically
GitLaw triggers automatically in certain situations:
| Feature | When GitLaw Runs |
| ----------------------- | ----------------------------------------------------------------- |
| Document Analysis | Identifying regulatory frameworks and jurisdictional requirements |
| Legal Issues Tracker | Researching each identified legal issue |
| Brief Citation Analysis | Verifying and expanding citations |
| Deliberation Mode | Background research by AI analysts |
***
## Saving Your Preferences
Set your default research mode:
1. Go to **Settings** → **Research Preferences**
2. Select default: **GitLaw Premium** or **Fast Search**
3. Your preference applies to all new research sessions
You can always override per-query using the dropdown.
***
## Troubleshooting
* **Switch to GitLaw Premium** - Fast Search uses semantic matching; Premium uses contextual retrieval which finds more nuanced sources
* Be more specific with jurisdiction and legal terms
* Try rephrasing with different legal terminology
* For international questions, try including terms in the native language
* Some older cases may not have online links
* Regional or state court cases may require paid database access
* International cases may link to local court websites
* Complex multi-jurisdictional questions take longer
* GitLaw Premium is more thorough but slower
* Try Fast Search for quicker preliminary results
* Make sure web research is enabled (globe icon should be highlighted)
* GitLaw searches live - if results seem old, the question may be matching older authoritative sources
* Try asking specifically for "recent" or specifying a date range
***
## Best Practices
Fast Search is fine for quick background research. For client advice, court filings, or formal opinions, use GitLaw Premium for better accuracy.
GitLaw is far more reliable than standard AI, but for citations in filed documents, verify through official sources.
Legal rules vary dramatically by jurisdiction. Always specify which state, circuit, or country is relevant.
For questions about recent developments, say "cases from 2023-2024" or "current regulations as of 2024."
***
## Next Steps
Full research capabilities and modes
Multi-analyst analysis for complex questions