# Attribution Faithfulness on AGNews Source: [Attribution Faithfulness on AGNews]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:45:11.266Z Evaluation of model attribution faithfulness on the AGNews dataset using the Faithfulness score metric. 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 | Attribution Faithfulness | | Dataset (including any stated split) | AGNews | | Metric | Faithfulness Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Faithfulness Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Faithfulness Score | Result date | Report paper | | --- | --- | --- | --- | | Tulu-2 13B | 41.7 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 32.3 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 28.1 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 26.5 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 24.9 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 24.8 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 23.7 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 19.9 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 18.5 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 14.9 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 13.6 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 12.7 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 9.9 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 8.7 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 7.7 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 4.9 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 7B | 3.5 | Not recorded | 6937ad576cfd488761a4ec96 | | Tulu-2 13B | 2.7 | Not recorded | 6937ad576cfd488761a4ec96 | ### Tulu-2 13B Faithfulness Score: 41.7. Result ID: 6996c82b5698665ec413d3aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Explanations","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 32.3. Result ID: 6996c82b5698665ec413d395. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Explanations","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 28.1. Result ID: 6996c82b5698665ec413d386. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Explanations","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 26.5. Result ID: 6996c82b5698665ec413d398. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Explanations","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 24.9. Result ID: 6996c82b5698665ec413d3a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Explanations","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 24.8. Result ID: 6996c82b5698665ec413d381. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"No-Training","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 23.7. Result ID: 6996c82b5698665ec413d393. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"No-Training","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 19.9. Result ID: 6996c82b5698665ec413d383. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Explanations","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 18.5. Result ID: 6996c82b5698665ec413d384. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"No-Training","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 14.9. Result ID: 6996c82b5698665ec413d396. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"No-Training","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 13.6. Result ID: 6996c82b5698665ec413d394. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Predictions","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 12.7. Result ID: 6996c82b5698665ec413d382. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Predictions","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 9.9. Result ID: 6996c82b5698665ec413d385. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Predictions","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 8.7. Result ID: 6996c82b5698665ec413d3a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"No-Training","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 7.7. Result ID: 6996c82b5698665ec413d397. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Predictions","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 4.9. Result ID: 6996c82b5698665ec413d3a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"No-Training","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 7B Faithfulness Score: 3.5. Result ID: 6996c82b5698665ec413d3a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Predictions","Word Constraint":"One-word"}. This record does not assert independent reproduction. ### Tulu-2 13B Faithfulness Score: 2.7. Result ID: 6996c82b5698665ec413d3a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Setup":"w/ Predictions","Word Constraint":"One-word"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.