Lease Renewal and Rent Adjustment Evidence Retrieval Benchmark
- Records
- 5000
- Size
- 0.2GB
- Format
- JSON
- Provider
MOBIUSI INC- Updated
- v1.02026-11-04
This benchmark covers lease provisions concerning fixed-term expiration, automatic renewal, renewal options, rent escalation, market rent review, and rent adjustment procedures. Its examples pair retrieval questions with supporting contract excerpts, testing whether systems can distinguish similar clauses, connect conditions across passages, and return complete, citable evidence. It is designed for developing, validating, and comparing retrieval-augmented generation systems for legal documents.
Overview
Dataset Insights
Preview
Sample Examples
Schema
Technical Specifications
| Field | Type | Description |
|---|---|---|
| file_name | string | File name |
| answer_summary | string | A concise conclusion that directly answers the retrieval query based on all relevant evidence. |
| evidence_spans | array | One or more original contract passages supporting the retrieval conclusion, suitable for direct quotation and traceable to the source. |
| retrieval_query | string | A question about renewal, rent adjustment, or related procedures that must be answered using the contract text. |
| source_document | string | The full text of the lease or relevant contract provisions to be searched; the original text source for evidence extraction. |
| renewal_analysis | object | An evidence-based summary of renewal arrangements, such as fixed-term expiration, automatic renewal, or renewal options. |
| evidence_completeness | object | A derived assessment of whether the retrieval results cover the key conditions for renewal and rent adjustment. |
| rent_adjustment_terms | object | An evidence-based summary of rent escalation, market rent review, and rent adjustment procedures. |
Trust
Compliance Statement
Authorization Type
Proprietary - Commercial AI Training License (No Redistribution)
Commercial Use
Requires exclusive subscription or authorization contract (monthly or per-invocation charging)
Privacy and Anonymization
No PII, no real company names, simulated scenarios follow industry standards
Compliance System
Compliant with China's Data Security Law / EU GDPR / supports enterprise data access logs
FAQ
Frequently Asked Questions
- Which contract topics are covered?
- The benchmark focuses on fixed-term expiration, automatic renewal, renewal options, rent escalation, market rent review, and rent adjustment procedures. Retrieval questions and supporting excerpts illustrate these tasks.
- What system capabilities can it evaluate?
- It can assess whether a system understands a retrieval question, locates one or more relevant contract passages, handles similar clauses and conditions spread across passages, and produces a direct, verifiable answer grounded in evidence.
- What are the main data fields?
- The main fields include the source contract text, retrieval query, evidence spans, renewal mechanism analysis, rent adjustment terms analysis, answer summary, and evidence completeness assessment.
- What should users check before using the benchmark?
- Confirm the delivery details, permitted uses, and licensing terms in the applicable dataset materials. The benchmark is intended for model development and evaluation, not as legal advice; qualified professionals should verify source language and applicable rules before making decisions about actual contracts.
Can't find the data you need?
Post a request and let data providers reach out to you.
Get this Dataset
High-quality data, ready for your next AI breakthrough.
Cite this Work
@dataset{Mobiusi2026,
title={Lease Renewal and Rent Adjustment Evidence Retrieval Benchmark},
author={MOBIUSI INC},
year={2026},
url={https://www.mobiusi.com/datasets/d538ab6f5ed372e34e6f2dc10e9d8d8f?dataset_scene_id=8},
urldate={2026-10-16},
keywords={lease renewal dataset,rent adjustment benchmark,lease evidence retrieval,legal document RAG,contract clause search,renewal clause analysis,rent escalation retrieval,evidence localization evaluation},
version={1.0}
}Using this in research? Please cite us.