# Privacy-preserving Query Rewriting on DelegateCI-Bench Medical Source: [Privacy-preserving Query Rewriting on DelegateCI-Bench Medical]() Collection index: [llms.txt]() Data updated: 2026-06-04T10:54:05.236Z Evaluation of Privacy-preserving Query Rewriting performance on the DelegateCI-Bench Medical dataset, measured by SLR, NE, EA, and Utilization metrics. 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 | Privacy-preserving Query Rewriting | | Dataset (including any stated split) | DelegateCI-Bench Medical | | Metric | Utilization | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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 - [Utilization](): Higher is better; unit: PERCENT. - [SLR](): Lower is better; unit: SCALAR. - [NE](): Lower is better; unit: SCALAR. - [EA](): Higher is better; unit: PERCENT. - [Average Utilization](): Higher is better; unit: PERCENT. - [Delta vs. Local](): Higher is better; unit: SCALAR. ## Recorded results | Method | Utilization | Result date | Report paper | | --- | --- | --- | --- | | Direct LLM | 79.5 | Not recorded | 6a2106dec10484bac23f0508 | | CI-guided reinforcement learning framework | 66.7 | Not recorded | 6a2106dec10484bac23f0508 | | Presidio(PII Only) | 64.2 | Not recorded | 6a2106dec10484bac23f0508 | | PUFT | 62.8 | Not recorded | 6a2106dec10484bac23f0508 | | CI-guided reinforcement learning framework | 62 | Not recorded | 6a2106dec10484bac23f0508 | | Local Only | 60.7 | Not recorded | 6a2106dec10484bac23f0508 | | Papillon | 59 | Not recorded | 6a2106dec10484bac23f0508 | | Papillon | 49.2 | Not recorded | 6a2106dec10484bac23f0508 | | PUFT | 49 | Not recorded | 6a2106dec10484bac23f0508 | | Local Only | 47.3 | Not recorded | 6a2106dec10484bac23f0508 | | CI-guided reinforcement learning framework | 41.2 | Not recorded | 6a2106dec10484bac23f0508 | | Papillon | 35 | Not recorded | 6a2106dec10484bac23f0508 | | Local Only | 34 | Not recorded | 6a2106dec10484bac23f0508 | | PUFT | 32.5 | Not recorded | 6a2106dec10484bac23f0508 | ### Direct LLM Utilization: 79.5. Result ID: 6a21593cfbc373592c1de0b6. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"raw query"}. This record does not assert independent reproduction. ### CI-guided reinforcement learning framework Utilization: 66.7. Result ID: 6a21593cfbc373592c1de0c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rewriter":"Qwen-2.5-3B (shared)","Local aggregator":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Presidio(PII Only) Utilization: 64.2. Result ID: 6a21593cfbc373592c1de0b7. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"rule-based PII"}. This record does not assert independent reproduction. ### PUFT Utilization: 62.8. Result ID: 6a21593cfbc373592c1de0c2. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"Llama-3.1-8B","Local aggregator":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### CI-guided reinforcement learning framework Utilization: 62. Result ID: 6a21593cfbc373592c1de0bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rewriter":"Qwen-2.5-3B (shared)","Local aggregator":"Qwen-2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Local Only Utilization: 60.7. Result ID: 6a21593cfbc373592c1de0c0. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"original query","Local aggregator":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Papillon Utilization: 59. Result ID: 6a21593cfbc373592c1de0bd. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"Qwen-2.5-7B","Local aggregator":"Qwen-2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Papillon Utilization: 49.2. Result ID: 6a21593cfbc373592c1de0c1. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"Llama-3.1-8B","Local aggregator":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### PUFT Utilization: 49. Result ID: 6a21593cfbc373592c1de0be. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"Qwen-2.5-7B","Local aggregator":"Qwen-2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Local Only Utilization: 47.3. Result ID: 6a21593cfbc373592c1de0bc. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"original query","Local aggregator":"Qwen-2.5-7B-Instruct"}. This record does not assert independent reproduction. ### CI-guided reinforcement learning framework Utilization: 41.2. Result ID: 6a21593cfbc373592c1de0bb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Rewriter":"Qwen-2.5-3B (shared)","Local aggregator":"Qwen-2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### Papillon Utilization: 35. Result ID: 6a21593cfbc373592c1de0b9. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"Qwen-2.5-1.5B","Local aggregator":"Qwen-2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### Local Only Utilization: 34. Result ID: 6a21593cfbc373592c1de0b8. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"original query","Local aggregator":"Qwen-2.5-1.5B-Instruct"}. This record does not assert independent reproduction. ### PUFT Utilization: 32.5. Result ID: 6a21593cfbc373592c1de0ba. [Reporting paper]() Recorded evaluation configuration: {"Rewriter":"Qwen-2.5-1.5B","Local aggregator":"Qwen-2.5-1.5B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.