# Question Answering on WebQ-QA Out-of-Domain (test) Source: [Question Answering on WebQ-QA Out-of-Domain (test)]() Collection index: [llms.txt]() Data updated: 2026-04-14T08:50:59.128Z Evaluation of model performance on the Out-of-Domain test split of the WebQ-QA dataset for Question Answering, measured using Precision and Truthfulness. 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 | Question Answering | | Dataset (including any stated split) | WebQ-QA Out-of-Domain (test) | | Metric | Precision | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 26 of 26 | | 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 - [Precision](): Higher is better; unit: PERCENT. - [Truthfulness](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision | Result date | Report paper | | --- | --- | --- | --- | | FAITH | 67.99 | Not recorded | 69ddca337d0172140ec79b27 | | FAITH\_sft+ppo | 67.31 | Not recorded | 69ddca337d0172140ec79b27 | | UAlign\_rag | 67.01 | Not recorded | 69ddca337d0172140ec79b27 | | FAITH\_sft | 66.94 | Not recorded | 69ddca337d0172140ec79b27 | | SFT\_rag | 66.93 | Not recorded | 69ddca337d0172140ec79b27 | | InFact | 66.92 | Not recorded | 69ddca337d0172140ec79b27 | | UAlign | 66.88 | Not recorded | 69ddca337d0172140ec79b27 | | Context-DPO | 66.75 | Not recorded | 69ddca337d0172140ec79b27 | | SFT | 66.46 | Not recorded | 69ddca337d0172140ec79b27 | | UAlign\_sft | 66.12 | Not recorded | 69ddca337d0172140ec79b27 | | RL-DPO | 65.99 | Not recorded | 69ddca337d0172140ec79b27 | | ICL-CoT | 65.97 | Not recorded | 69ddca337d0172140ec79b27 | | DTA | 61.24 | Not recorded | 69ddca337d0172140ec79b27 | | FAITH | 58.04 | Not recorded | 69ddca337d0172140ec79b27 | | Context-DPO | 57.32 | Not recorded | 69ddca337d0172140ec79b27 | | InFact | 56.98 | Not recorded | 69ddca337d0172140ec79b27 | | UAlign\_rag | 56.97 | Not recorded | 69ddca337d0172140ec79b27 | | DTA | 56.53 | Not recorded | 69ddca337d0172140ec79b27 | | UAlign | 56.47 | Not recorded | 69ddca337d0172140ec79b27 | | FAITH\_sft+ppo | 55.48 | Not recorded | 69ddca337d0172140ec79b27 | | UAlign\_sft | 55.34 | Not recorded | 69ddca337d0172140ec79b27 | | ICL-CoT | 53.43 | Not recorded | 69ddca337d0172140ec79b27 | | SFT\_rag | 53.14 | Not recorded | 69ddca337d0172140ec79b27 | | SFT | 52.24 | Not recorded | 69ddca337d0172140ec79b27 | | RL-DPO | 52.01 | Not recorded | 69ddca337d0172140ec79b27 | | FAITH\_sft | 51.99 | Not recorded | 69ddca337d0172140ec79b27 | ### FAITH Precision: 67.99. Result ID: 69ddfecc47f34ce924c57dc4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### FAITH\_sft+ppo Precision: 67.31. Result ID: 69ddfecc47f34ce924c57dc5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### UAlign\_rag Precision: 67.01. Result ID: 69ddfecc47f34ce924c57dc1. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### FAITH\_sft Precision: 66.94. Result ID: 69ddfecc47f34ce924c57dc6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### SFT\_rag Precision: 66.93. Result ID: 69ddfecc47f34ce924c57dbc. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### InFact Precision: 66.92. Result ID: 69ddfecc47f34ce924c57dc3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### UAlign Precision: 66.88. Result ID: 69ddfecc47f34ce924c57dbf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### Context-DPO Precision: 66.75. Result ID: 69ddfecc47f34ce924c57dc2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### SFT Precision: 66.46. Result ID: 69ddfecc47f34ce924c57dbb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### UAlign\_sft Precision: 66.12. Result ID: 69ddfecc47f34ce924c57dc0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### RL-DPO Precision: 65.99. Result ID: 69ddfecc47f34ce924c57dbd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### ICL-CoT Precision: 65.97. Result ID: 69ddfecc47f34ce924c57dba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### DTA Precision: 61.24. Result ID: 69ddfecc47f34ce924c57dbe. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3-8B"}. This record does not assert independent reproduction. ### FAITH Precision: 58.04. Result ID: 69ddfecc47f34ce924c57dd1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### Context-DPO Precision: 57.32. Result ID: 69ddfecc47f34ce924c57dcf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### InFact Precision: 56.98. Result ID: 69ddfecc47f34ce924c57dd0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### UAlign\_rag Precision: 56.97. Result ID: 69ddfecc47f34ce924c57dce. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### DTA Precision: 56.53. Result ID: 69ddfecc47f34ce924c57dcb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### UAlign Precision: 56.47. Result ID: 69ddfecc47f34ce924c57dcc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### FAITH\_sft+ppo Precision: 55.48. Result ID: 69ddfecc47f34ce924c57dd2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### UAlign\_sft Precision: 55.34. Result ID: 69ddfecc47f34ce924c57dcd. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### ICL-CoT Precision: 53.43. Result ID: 69ddfecc47f34ce924c57dc7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### SFT\_rag Precision: 53.14. Result ID: 69ddfecc47f34ce924c57dc9. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### SFT Precision: 52.24. Result ID: 69ddfecc47f34ce924c57dc8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### RL-DPO Precision: 52.01. Result ID: 69ddfecc47f34ce924c57dca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. ### FAITH\_sft Precision: 51.99. Result ID: 69ddfecc47f34ce924c57dd3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-v0.1"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.