For directors, managing agents and leaseholders: three structural reasons ChatGPT, Gemini, and Copilot give confident but wrong answers about a lease, and why the tool you actually need is one designed for the job.
Information only, not legal advice. Always take professional advice before acting. England and Wales.
A lease is not a blog post. It is a formal document with a specific structure, sitting inside 40 years of statute and case law. Asking ChatGPT a lease question is like asking a sommelier to fix your boiler, not because they are stupid, but because the task is outside the training. This page explains the three places where the generic tools fall down, and what to do about it.
The most basic failure happens before the model has started reasoning. It happens at the point of reading the document.
Large language models do not read text the way you do. They are next-token predictorsA transformer-based LLM generates output one token at a time by predicting the most statistically likely next token given everything before it. It does not "look up" or "copy" text. Even when the input document is fully in context, the output is generated probabilistically. See Liu et al, Lost in the Middle, 2023., they generate the most statistically likely next word given everything that has come before. When that process meets a PDF, three specific things go wrong.
For a lease, that hallucination lands on figures that matter. Apportionment percentagesThe fraction of the total service charge payable by a flat, typically expressed as a percentage or a defined share. One wrong digit on apportionment can change a leaseholder's bill by hundreds or thousands of pounds per year.. Ground rent figures. Unexpired term. The £250 per leaseholderThe consultation threshold under Landlord and Tenant Act 1985, s.20 for qualifying works. If the cost to any one leaseholder exceeds £250, the landlord must consult. Miss the threshold and recovery is capped at £250 per leaseholder. s.20 threshold. The 18-month time barLTA 1985, s.20B. Costs must be demanded within 18 months of being incurred, or notified in writing with a statement that a demand will follow. Miss it and costs become unrecoverable through the service charge.. A single hallucinated digit changes the answer.
Leases are scanned. Scans have page breaks, tight margins, and sometimes text that gets clipped. When an LLM meets a sentence that ends mid-phrase, it does not stop, because stopping mid-phrase is statistically unlikely. It fills in the words that the pattern suggests "should" come next. Those words were never in your lease.
And there is "lost in the middle"Liu et al (2023) showed that LLMs perform markedly worse at retrieving specific information from the middle of long documents compared to the start or end. For a 40-page lease, the most commercially consequential clauses are often in the schedules near the end, or in definitions near the start, but variations, assignments, and side-letters are frequently buried in the middle.: the well-documented finding that LLMs reliably miss specific facts buried deep in long documents. A lease is exactly the kind of long document where the clause that matters is buried in Schedule 5 Part II.
None of this is a flaw that "prompt better" can fix. It is how transformer architectures work.
Even if a model could read the document perfectly, the next failure is conceptual. An LLM sees a wall of text. A lease is a structured object.
In computer science, an ontologyA formal representation of the concepts in a domain and the relationships between them. Knowledge graphs (Google's Knowledge Graph, medical ontologies like SNOMED CT, legal ontologies like LKIF) encode this structure so that machines can reason about "A is a type of B" or "C overrides D" rather than treating every sentence as flat text. is a formal structure that encodes the concepts in a domain and how they relate to each other. A lease has a rich ontology: a main body that incorporates schedules, schedules with parts and sub-paragraphs, definitions in clause 1 that govern every later clause, cross-references that mean clause 4.7(b)(iii) only makes sense alongside Schedule 2 paragraph 5, and deeds of variationA deed of variation is a supplementary deed that formally amends the original lease. It can change rent review mechanisms, permitted use, alterations, or add rights. Once executed, it becomes part of the lease for all purposes, but it is a separate document filed alongside. The original lease wording remains, but is overridden in specific places. that override the original wording years later.
Your lease, dated 1985, says at Clause 3.2 that the lessor insures. Schedule 5 Part II, added in a 1998 supplemental deed, says that where the building is converted to flats, the RMC insures. A 2019 deed of variation extends RMC insurance to include terrorism cover. The answer to "who insures?" depends on reading all three, in the right order, and understanding that the later document overrides the earlier one. An LLM reading these as flat text has no model of that hierarchy.
There are other ontological features a generic model has no representation of: the demised premises chainThe demise defines what the leaseholder owns (usually the inside skin of the flat: internal walls, floor coverings, non-load-bearing partitions) and what they don't (structure, roof, foundations, common parts). The boundary between demised and retained parts is the single most contested question in water-leak and repair disputes. Get the demise wrong and you get the repair liability wrong., which defines who owns what and who repairs what; the covenant chainWhen a lease is sub-let, obligations flow through: the head-lessee owes the freeholder, the under-lessee owes the head-lessee. The under-lessee is rarely in direct privity with the freeholder. This matters enormously for enforcement and for Section 20 consultation, which must reach the qualifying person. when a flat is sub-let; the distinction between covenants and regulationsCovenants are binding promises in the lease itself, enforceable via forfeiture or damages. Regulations are rules the landlord can make under a general clause (often "the landlord may make reasonable regulations"). Regulations are weaker, more easily challenged as unreasonable, and cannot extend beyond what the lease permits. A challenge that treats them as equivalent is a frequent AI error.; and reservationsRights reserved to the landlord (or kept back from what was demised), such as rights of access, rights to run services, or rights to build. Reservations are a separate schedule from the demise itself and are easy to miss. They are often the deciding factor in alteration consents..
To a general-purpose model, all of this is flat prose. To a director trying to answer a leaseholder's challenge, these distinctions are the case.
The third failure is contextual. Even with a perfectly-read, perfectly-structured lease, the answer depends on statute, case law, and tribunal practice. The lease text is only half the answer.
A leasehold question in England and Wales sits inside a framework that has been built up across forty years of statute. The foundational instruments include the Landlord and Tenant Act 1985LTA 1985. The backbone of residential leasehold law. Governs service charge reasonableness (s.19), consultation (s.20), the 18-month time bar (s.20B), account summaries (s.21), and tribunal jurisdiction over service charges (s.27A)., the Leasehold Reform, Housing and Urban Development Act 1993LRHUDA 1993. Governs collective enfranchisement (leaseholders buying the freehold together) and individual lease extensions under the old regime., the Commonhold and Leasehold Reform Act 2002CLRA 2002. Introduced Right to Manage (RTM), reformed lease extension, and created the Leasehold Valuation Tribunal (now First-tier Tribunal Property Chamber)., the Leasehold and Freehold Reform Act 2024LFRA 2024. Enacted in May 2024. Abolishes the two-year ownership qualification for lease extension, extends new lease terms to 990 years at peppercorn rent, bans most new-build leasehold houses, and sets the framework for future ground rent reform., and the Building Safety Act 2022BSA 2022. Passed in response to Grenfell. Imposes a regulatory regime for higher-risk buildings, creates the Building Safety Regulator, and, crucially for service charges, Schedule 8 protects qualifying leaseholders from paying for historic safety remediation..
A lease clause that looks valid on its face can be unenforceable under s.19 LTA 1985LTA 1985, s.19. Service charges must be reasonable in amount and the works reasonably incurred. The tribunal can determine what is reasonable. A lease clause that says otherwise cannot override this statutory protection. (reasonableness), or void under s.20BLTA 1985, s.20B. Costs must be demanded within 18 months of being incurred. A written notification within 18 months preserves the right to demand later. Outside these rules, costs become unrecoverable through the service charge. (the 18-month time bar), or overridden by a right to manageUnder CLRA 2002 Part II, qualifying leaseholders can form an RTM company and take over management without paying the freeholder or proving fault. Once RTM is acquired, management obligations and service charge authority transfer to the RTM company, regardless of what the original lease says about who manages. claim. Reading the lease in isolation can lead you to exactly the wrong answer.
Statute alone is not enough. The courts interpret these provisions, and the interpretation shifts. Daejan Investments Ltd v Benson [2013] UKSC 14The leading Supreme Court authority on s.20 dispensation. Before Daejan, dispensation was treated as something close to a penalty for landlords. The Supreme Court reframed the test: dispensation should be granted unless leaseholders can show they have suffered prejudice as a result of the consultation failure. This flipped the practical risk. Read at The Supreme Court. reframed the test for s.20 dispensation. Phillips v Francis [2014][2014] EWCA Civ 1395. Reversed the earlier "aggregation" approach to s.20 consultation, confirming that the threshold applies to each "set of qualifying works" separately, not to the total annual spend. This is the reason you often see consultation carried out on specific projects rather than on annual budgets. reset how consultation thresholds are applied to annual budgets. A model trained on pre-2013 material will give you pre-Daejan answers to post-Daejan questions.
Generic AI may have heard of these statutes in training. It does not reliably know which sections apply to your question, what they cap, how the tribunal has interpreted them, or which 2024 changes now override the 1993 text.
The three failure modes don't just produce bad answers. They produce confident-sounding bad answers, at speed. That combination has a cost on both sides of the correspondence.
Leaseholders arrive with AI-drafted letters that cite made-up clauses, fabricate apportionment figures, or misapply s.20. The prose sounds authoritative. The statutory references are correctly named but wrongly applied. Hours get burnt rebutting each letter. The relationship sours. The actual underlying issue, if there is one, gets lost in the noise.
See our page on AI-drafted leaseholder disputes for the response pattern.
Writing to your freeholder with a ChatGPT-drafted challenge that misquotes your own lease can:
Before you press send, check the clauses you are citing are actually in your lease. Our Talk-to-us service reads every clause and writes a brief that strengthens a challenge rather than weakens it.
All three failure modes can be addressed. Not by a better prompt. By a different architecture.
For the PDF parsing problem: open-source OCR combined with LLM multimodal parsing, wrapped in a custom validation layer that double- and triple-checks the extracted text for structure, clause boundaries, and figures during parsing. The reconciled output goes into the knowledge graph; the raw OCR does not. Off-the-shelf models do the reading; the custom layer does the checking.
For the ontology problem: a knowledge graph that encodes clause hierarchy, schedules, cross-references, definitions, and variations as first-class structure, so the system can traverse them in the right order.
For the legal construct problem: UK leasehold statute and the governing case law pre-processed as rules that get applied to each answer, not hoped-for recall from pre-training.
And on top of all three: a cross-check layer that runs multiple independent responses, removes outliers, and flags disagreement honestly instead of resolving it silently.
Open-source OCR plus LLM multimodal parsing, wrapped in a custom validation layer that double- and triple-checks during parsing. Knowledge graph of clause hierarchy. Pre-processed UK statute and governing case law. A multi-response cross-check designed to flag disagreement rather than resolve it silently when generating answers, with answers tied back to the specific clause and page in your own lease. Where the system can't reach confidence, it is designed to say so rather than guess.
How LEASE-iQ works → Try it free →All links verified at the date of last review shown at the top of this page. If a link has moved, please tell us.
LEASE-iQ is designed around the three failure modes above, not around a better prompt.
How LEASE-iQ works → Try it free →