# Entity-Swap Question Answering on NQ-Swap Source: [Entity-Swap Question Answering on NQ-Swap]() Collection index: [llms.txt]() Data updated: 2026-06-04T07:28:39.890Z Evaluation of Entity-Swap Question Answering performance on the NQ-Swap dataset, reporting Exact Match (EM). 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 | Entity-Swap Question Answering | | Dataset (including any stated split) | NQ-Swap | | Metric | Exact Match (EM) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Exact Match (EM)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact Match (EM) | Result date | Report paper | | --- | --- | --- | --- | | CAD | 84.7 | Not recorded | 6a210686c10484bac23f010c | | DeCoRe (static) | 79.06 | Not recorded | 6a210686c10484bac23f010c | | Greedy | 76.11 | Not recorded | 6a210686c10484bac23f010c | | DoLa (low) | 75.98 | Not recorded | 6a210686c10484bac23f010c | | DCO | 75.33 | Not recorded | 6a210686c10484bac23f010c | | DoLa (high) | 75.26 | Not recorded | 6a210686c10484bac23f010c | | ITI | 74.76 | Not recorded | 6a210686c10484bac23f010c | | CAD | 74.21 | Not recorded | 6a210686c10484bac23f010c | | AD | 74.02 | Not recorded | 6a210686c10484bac23f010c | | CD | 68.37 | Not recorded | 6a210686c10484bac23f010c | | DeCoRe (static) | 64.43 | Not recorded | 6a210686c10484bac23f010c | | DCO | 62.96 | Not recorded | 6a210686c10484bac23f010c | | DoLa (high) | 60.98 | Not recorded | 6a210686c10484bac23f010c | | DoLa (low) | 60.77 | Not recorded | 6a210686c10484bac23f010c | | Greedy | 60.62 | Not recorded | 6a210686c10484bac23f010c | | AD | 60.51 | Not recorded | 6a210686c10484bac23f010c | | ITI | 51.08 | Not recorded | 6a210686c10484bac23f010c | ### CAD Exact Match (EM): 84.7. Result ID: 6a212925fbc373592c1c5171. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### DeCoRe (static) Exact Match (EM): 79.06. Result ID: 6a212925fbc373592c1c5175. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### Greedy Exact Match (EM): 76.11. Result ID: 6a212925fbc373592c1c516e. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### DoLa (low) Exact Match (EM): 75.98. Result ID: 6a212925fbc373592c1c5172. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### DCO Exact Match (EM): 75.33. Result ID: 6a212925fbc373592c1c5176. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### DoLa (high) Exact Match (EM): 75.26. Result ID: 6a212925fbc373592c1c5173. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### ITI Exact Match (EM): 74.76. Result ID: 6a212925fbc373592c1c516f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### CAD Exact Match (EM): 74.21. Result ID: 6a212925fbc373592c1c5168. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. ### AD Exact Match (EM): 74.02. Result ID: 6a212925fbc373592c1c5174. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### CD Exact Match (EM): 68.37. Result ID: 6a212925fbc373592c1c5170. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama-3-70B"}. This record does not assert independent reproduction. ### DeCoRe (static) Exact Match (EM): 64.43. Result ID: 6a212925fbc373592c1c516c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. ### DCO Exact Match (EM): 62.96. Result ID: 6a212925fbc373592c1c516d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. ### DoLa (high) Exact Match (EM): 60.98. Result ID: 6a212925fbc373592c1c516a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. ### DoLa (low) Exact Match (EM): 60.77. Result ID: 6a212925fbc373592c1c5169. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. ### Greedy Exact Match (EM): 60.62. Result ID: 6a212925fbc373592c1c5166. [Reporting paper]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. ### AD Exact Match (EM): 60.51. Result ID: 6a212925fbc373592c1c516b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. ### ITI Exact Match (EM): 51.08. Result ID: 6a212925fbc373592c1c5167. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model":"Llama-3-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.