# Hallucination

> A hallucination occurs when an AI language model states something confidently that is untrue or unsupported by the source. For example, it might invent a unit price or an exclusion that does not appear in a subcontractor's proposal.

- Stages: Estimating, Preconstruction
- Concepts: LLMs, Evaluation
- Published: 2026-08-28
- Canonical: https://buildr.com/library/hallucination

## Why it matters in construction

In estimating, a hallucinated fact can become a margin problem. If a model reads a mechanical proposal and reports "includes seismic bracing" when the sub excluded it, the gap may surface after award. If an RFP summary invents a liquidated-damages figure, the go/no-go discussion starts with a number that does not exist.

The output can look polished. A hallucinated exclusion may be formatted exactly like a real one. A model can state "$12,000" with the same confidence whether the number came from the proposal or not.

## How it works

Language models can hallucinate because they generate text instead of looking up verified facts.

1. **Prediction, not lookup.** The model produces the likely continuation of the text so far. If the true answer is missing, it may still produce a plausible-sounding answer.
2. **Gaps in the prompt.** When a tool asks "what is the bond rate?" and the proposal never mentions bonding, the model may supply a typical rate rather than "not stated."
3. **Long documents.** Important details can be missed in long documents. A 40-page proposal with exclusions on page 31 needs careful retrieval and review.
4. **Confidence is not proof.** The model may use the same tone whether it found the fact or invented it.

Give the model source documents instead of relying on memory. Require it to quote the passage it used. Make "not found" a valid answer. Before using the tool on live bids, test it on proposals with known answers and measure its misses.

## Example in practice

Consider a GC's estimating team piloting an AI leveling tool on a $4.2M electrical package with six proposals. On the first pass, the tool reports that all six include temporary power. The estimator checks the sources. Four say it explicitly, one is silent, and one excludes it in a footnote on page three. Two of the six answers were hallucinated.

The team reconfigures the tool to require a quoted passage for every inclusion and to return "not stated" when nothing turns up. On the rerun, it flags the silent proposal for follow-up and catches the footnote exclusion, worth roughly $65,000 on that job. The team adopts a new rule: no leveling cell is accepted without a visible source.

## Go deeper

- [AI for Estimators: 5 Practical Uses that Work Today (Not Someday)](/blog/ai-for-construction-estimators.md)
- [AI Bid Leveling in Construction: A GC's Practical Guide](/blog/ai-bid-leveling.md)
- [The Pros and Cons of ChatGPT in Construction](/blog/chatgpt-construction.md)

## Related terms

- [Grounding and Citations](/library/grounding-and-citations.md): Grounding ties an AI answer to specific source material rather than the model's general knowledge. Citations show where each claim came from. In construction, that might mean pointing to Section 09 29 00, paragraph 3.4, for a level 5 finish requirement.
- [Human-in-the-Loop](/library/human-in-the-loop.md): Human-in-the-loop is an AI design pattern in which a person reviews, corrects, or approves the model's output before it takes effect. In construction, an estimator still owns the award and a BD lead still approves a pipeline update, while the AI handles reading and drafting.
- [AI Evals](/library/ai-evals.md): AI evals are structured tests that measure how well an AI system performs on a defined task using examples with known answers. A construction firm can use them to test whether a tool reads its sub proposals or RFPs accurately before relying on it on bid day.
- [Retrieval-Augmented Generation (RAG)](/library/retrieval-augmented-generation.md): Retrieval-Augmented Generation (RAG) finds relevant pages in a company's own documents and gives them to an AI language model before it answers. It grounds a construction team's responses in its actual specs, proposals, and project history instead of the model's general knowledge.
- [Large Language Model (LLM)](/library/large-language-model.md): A large language model (LLM) is an AI system trained on large amounts of text that can read, summarize, and generate language. In construction, it can help parse RFPs, sub proposals, and specifications for preconstruction teams.

## Referenced by

- [AI Bid Leveling](/library/ai-bid-leveling.md): AI bid leveling reads subcontractor proposals, pulls out prices and exclusions, and puts them into a like-for-like comparison. It helps estimators judge complete scope before they award work instead of treating the lowest number as the answer.
- [AI Cash Flow Forecasting](/library/ai-cash-flow-forecasting.md): AI cash flow forecasting projects a construction company's monthly cash position from backlog billing schedules, weighted pipeline, historical pay-app timing, and retainage patterns. It can show leadership a potential cash shortfall before it arrives.
- [AI Plan and Spec Review](/library/ai-plan-and-spec-review.md): AI plan and spec review uses language models to compare a construction drawing set with its specification book. It flags conflicts, missing information, and risk items for the preconstruction team to review before pricing.
- [AI Proposal Generation](/library/ai-proposal-generation.md): AI proposal generation uses language models to draft construction proposal content, such as approach narratives, past project descriptions, and team bios, from a general contractor's own history and the RFP requirements. The pursuit team then reviews and edits the draft.
- [AI RFP Analysis](/library/ai-rfp-analysis.md): AI RFP analysis uses language models to read a construction request for proposals, extract the requirements, deadlines, evaluation criteria, and risk terms, and summarize them so a general contractor can decide whether and how to pursue the job.
- [Context Window](/library/context-window.md): A context window is the amount of text, measured in tokens, that an AI language model can consider in one request. It limits how much of a construction spec book or proposal set the model can see at once.
- [Data Readiness](/library/data-readiness.md): Data readiness is how complete, consistent, and accessible a construction company's project, pipeline, cost, and staffing records are. It determines whether AI tools can produce useful forecasts and comparisons or confident answers built on gaps.
- [Natural Language Querying](/library/natural-language-querying.md): Natural language querying lets a construction team ask questions about business data in plain English, such as 'what is our weighted pipeline for Q4' or 'which superintendents are free in March,' and get answers from the CRM, backlog, and workforce plan without building reports or formulas.
- [Prompt Engineering](/library/prompt-engineering.md): Prompt engineering is the practice of writing instructions, examples, and context for an AI language model so it produces reliable output, such as telling it exactly how to classify exclusions in a construction subcontractor proposal.
- [Reasoning Models](/library/reasoning-models.md): Reasoning models are AI language models designed to spend more effort on a problem before answering. They can be useful for multi-step construction judgments, such as reconciling a spec conflict across three divisions or scoring a go/no-go with competing criteria.
- [Structured Data Extraction](/library/structured-data-extraction.md): Structured data extraction uses AI to turn unstructured construction documents, such as sub proposals, RFPs, and specs, into typed fields like line items, prices, exclusions, and dates that can be sorted, compared, and loaded into an estimate or CRM.

## FAQ

### Why do language models hallucinate?

They generate likely text rather than verifying facts. When the answer is absent from the prompt or available source material, a model may produce something plausible instead of saying it does not know.

### Can hallucination be eliminated?

Not completely. Grounding the model in your documents, requiring citations, using structured output, and keeping a person on the award decision can reduce the risk.

### How do I tell if an AI tool is hallucinating on my bids?

Ask it to show the source. If an extracted number or exclusion cannot be traced back to a specific line in the proposal, treat it as unverified. Tools that cannot show source text should not be trusted with pricing.