Production Set 08 // Privilege Detection
AI privilege review, what it catches and what it misses.
VERIFIED 21 APR 2026 // INDEPENDENT REFERENCE // NOT LEGAL ADVICE
Privilege review remains the single largest cost driver in modern eDiscovery. A 5 TB corporate matter may contain tens of thousands of documents requiring individual privilege assessment, and the consequences of error, either inadvertent production or over-withholding, are significant. AI is genuinely useful here, but the accuracy limitations and failure modes require attorney supervision and a 502(d) backstop.
Section 01 // Volume Problem
The privilege review problem at volume
In a typical 5 TB corporate investigation, a document population of 500,000 documents might yield 30,000 to 80,000 documents flagged as potentially privileged in keyword-based first-pass culling. Manual attorney review at $200 to $350 per hour, even at 50 to 80 documents per hour, can cost $75,000 to $160,000 in privilege review alone before any other review cost. Privilege logging requirements add further attorney time.
AI privilege detection replaces or augments the keyword-flagging step with a model that understands privilege signals contextually: attorney-client communications, work product preparation, legal advice requests, and the forwarded-chain propagation of privilege. The potential cost reduction is significant, but only if the AI is accurate enough and the validation methodology is documented.
Section 02 // How It Works
How AI privilege detection works
Modern AI privilege detection, as implemented in Relativity aiR for Privilege, EverlawAI's privilege module, and similar tools, uses a combination of signals. Structural signals: presence of attorney email addresses or names in the To / From / CC fields, header analysis for legal hold or counsel communications. Content signals: LLM analysis of the document text for legal advice requests, attorney-client discussion patterns, legal strategy language, and work product indicators. Propagation signals: forwarded chain analysis that flags a document as privileged if it contains a privileged communication embedded in a reply chain, even if the outer email is routine.
Relativity's aiR for Privilege is the most mature implementation as of September 2026. Relativity and its partners report strong first-pass accuracy on attorney-client and work-product documents in typical corporate litigation populations, but Relativity does not publish a single standardized accuracy benchmark, so treat any specific percentage as vendor- or case-study-reported rather than an independent figure. EverlawAI's privilege module is broadly comparable. Accuracy varies significantly by document type.
Section 03 // Accuracy Log
Accuracy by document type
| Document Type | Typical Accuracy | Key Challenge |
|---|---|---|
| Direct attorney-client email | 90-97% | Few; attorney names and addresses clear |
| Work product (legal memos) | 88-95% | Identifying 'anticipation of litigation' |
| Forwarded email chains (partial quote) | 75-85% | Embedded privileged content in routine outer email |
| Business advice vs legal advice | 70-82% | Mixed-purpose documents; hard line not obvious |
| Handwritten notes (OCR) | 65-75% | OCR quality; attorney-client relationship not always clear |
| Spreadsheets with embedded text | Variable | Structured-data privilege detection is challenging |
Approximate benchmarks // Last verified Apr 2026
Section 04 // 502(d) Backstop
Rule 502(d) as the essential backstop
Federal Rule of Evidence 502(d) allows a court to order that inadvertent production of privileged or work-product material does not constitute a waiver in the pending proceeding or in any other federal or state proceeding. This is the essential backstop for any AI-assisted privilege review.
FED. R. EVID. 502(d) // VERBATIM
Judge Peck's model 502(d) order language (developed and refined through the Da Silva Moore, Biomet, and Rio Tinto matters) is the standard template: it covers inadvertent production, requires prompt notification and return of produced privileged documents, and applies non-waiver protections to all subsequent proceedings. Any AI-assisted privilege review should be covered by a 502(d) order before production begins. The Sedona Conference has published recommended 502(d) order language, and most courts in jurisdictions with frequent complex commercial litigation have a standing template available.
Section 05 // Failure Modes
Hard cases: where AI privilege detection fails
- •Business-advice versus legal-advice line. In-house counsel routinely provide both legal advice and business advice in the same communication. Attorney-client privilege applies to the legal advice but not the business advice, and the line is a question of fact for each document. Current AI models struggle with the mixed-purpose document because the privilege determination turns on purpose, not content.
- •Joint defence and common-interest privilege. Communications between co-defendants or parties with a common legal interest may be privileged under the joint-defence doctrine. AI models are not consistently trained on joint-defence privilege signals and frequently miss this category.
- •Crime-fraud exception. Where a party claims the crime-fraud exception to privilege, the court conducts an in camera review. AI cannot assess the crime-fraud exception because it requires a legal determination, not a document-classification determination.
- •Partial redaction within a document. A document may contain both privileged and non-privileged content. AI tools that classify at the document level, not the text-segment level, will either over-withhold or under-redact on partial-privilege documents.
Section 06 // FAQ