# Question Answering on TriviaQA (AUC, F95, AUP) Source: [Question Answering on TriviaQA (AUC, F95, AUP)]() Collection index: [llms.txt]() Data updated: 2026-04-20T07:34:03.079Z Evaluation of model performance on the TriviaQA dataset for Question Answering, reporting AUC, F95, and AUP 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 | Question Answering | | Dataset (including any stated split) | TriviaQA | | Metric | AUC | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [AUC](): Higher is better; unit: SCALAR. - [F95](): Higher is better; unit: PERCENT. - [AUP](): Higher is better; unit: SCALAR. ## Recorded results | Method | AUC | Result date | Report paper | | --- | --- | --- | --- | | SIVR (Ours) | 89.48 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | TAD | 87.02 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | SAPLMA | 83.7 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | SAR | 83.66 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | Lookback Lens | 82.94 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | SATMD + MSP | 82.45 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | SE | 81.65 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | Entropy | 78.58 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | Perplexity | 78.18 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | Max Prob | 77.3 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | Temp-Scaled | 76.65 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | Energy | 67.5 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | CoE-C | 65.14 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | P(True) | 65.04 | Not recorded | 69e5b2d67d0172140ec7ddc8 | | CoE-R | 37.75 | Not recorded | 69e5b2d67d0172140ec7ddc8 | ### SIVR (Ours) AUC: 89.48. Result ID: 69e5d66a47f34ce924cbaca1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### TAD AUC: 87.02. Result ID: 69e5d66a47f34ce924cbaca0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### SAPLMA AUC: 83.7. Result ID: 69e5d66a47f34ce924cbac9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### SAR AUC: 83.66. Result ID: 69e5d66a47f34ce924cbac9a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Lookback Lens AUC: 82.94. Result ID: 69e5d66a47f34ce924cbac9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### SATMD + MSP AUC: 82.45. Result ID: 69e5d66a47f34ce924cbac9d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### SE AUC: 81.65. Result ID: 69e5d66a47f34ce924cbac99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Entropy AUC: 78.58. Result ID: 69e5d66a47f34ce924cbac96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Perplexity AUC: 78.18. Result ID: 69e5d66a47f34ce924cbac95. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Max Prob AUC: 77.3. Result ID: 69e5d66a47f34ce924cbac94. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Temp-Scaled AUC: 76.65. Result ID: 69e5d66a47f34ce924cbac97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### Energy AUC: 67.5. Result ID: 69e5d66a47f34ce924cbac98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### CoE-C AUC: 65.14. Result ID: 69e5d66a47f34ce924cbac9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### P(True) AUC: 65.04. Result ID: 69e5d66a47f34ce924cbac93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. ### CoE-R AUC: 37.75. Result ID: 69e5d66a47f34ce924cbac9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.