# Legal Contract Revision on PrivacyQA Source: [Legal Contract Revision on PrivacyQA]() Collection index: [llms.txt]() Data updated: 2026-04-14T10:11:50.935Z Evaluation of model performance on revising legal contracts using the PrivacyQA dataset. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Legal Contract Revision | | Dataset (including any stated split) | PrivacyQA | | Metric | CQ | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [CQ](): Higher is better; unit: PERCENT. - [RRR](): Higher is better; unit: PERCENT. - [TES](): Higher is better; unit: PERCENT. ## Recorded results | Method | CQ | Result date | Report paper | | --- | --- | --- | --- | | RCBSF | 87.75 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 84.67 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 84.55 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 82.33 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 81.56 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 80.12 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RCBSF | 79.88 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 79.12 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 78.56 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 77.88 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 77.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 77.23 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 76.89 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 75.67 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 74.34 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 73.89 | Not recorded | 69ddca1e7d0172140ec79aa1 | | RAG | 73.56 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 72.56 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 71.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Iteration | 71.34 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 71.23 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 70.23 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 68.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | | CoT | 67.89 | Not recorded | 69ddca1e7d0172140ec79aa1 | | Standard | 65.45 | Not recorded | 69ddca1e7d0172140ec79aa1 | ### RCBSF CQ: 87.75. Result ID: 69de12de47f34ce924c60efa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RCBSF CQ: 84.67. Result ID: 69de12de47f34ce924c60ee6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### RCBSF CQ: 84.55. Result ID: 69de12de47f34ce924c60ef0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### RCBSF CQ: 82.33. Result ID: 69de12de47f34ce924c60eeb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Iteration CQ: 81.56. Result ID: 69de12de47f34ce924c60ef9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RAG CQ: 80.12. Result ID: 69de12de47f34ce924c60ef8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RCBSF CQ: 79.88. Result ID: 69de12de47f34ce924c60ef5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### Iteration CQ: 79.12. Result ID: 69de12de47f34ce924c60eef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### Iteration CQ: 78.56. Result ID: 69de12de47f34ce924c60ee5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### Iteration CQ: 77.88. Result ID: 69de12de47f34ce924c60eea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### RAG CQ: 77.45. Result ID: 69de12de47f34ce924c60eee. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### RAG CQ: 77.23. Result ID: 69de12de47f34ce924c60ee4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### CoT CQ: 76.89. Result ID: 69de12de47f34ce924c60ef7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### RAG CQ: 75.67. Result ID: 69de12de47f34ce924c60ee9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Standard CQ: 74.34. Result ID: 69de12de47f34ce924c60ef6. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Chat"}. This record does not assert independent reproduction. ### CoT CQ: 73.89. Result ID: 69de12de47f34ce924c60ee3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### RAG CQ: 73.56. Result ID: 69de12de47f34ce924c60ef3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### CoT CQ: 72.56. Result ID: 69de12de47f34ce924c60eed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### Standard CQ: 71.45. Result ID: 69de12de47f34ce924c60ee2. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Base"}. This record does not assert independent reproduction. ### Iteration CQ: 71.34. Result ID: 69de12de47f34ce924c60ef4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### CoT CQ: 71.23. Result ID: 69de12de47f34ce924c60ee8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### Standard CQ: 70.23. Result ID: 69de12de47f34ce924c60eec. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LawLLM-7B"}. This record does not assert independent reproduction. ### Standard CQ: 68.45. Result ID: 69de12de47f34ce924c60ee7. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B"}. This record does not assert independent reproduction. ### CoT CQ: 67.89. Result ID: 69de12de47f34ce924c60ef2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. ### Standard CQ: 65.45. Result ID: 69de12de47f34ce924c60ef1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LexiLaw-6B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.