# Question Answering on SQuAD Abstract (Mean per-step regret) Source: [Question Answering on SQuAD Abstract (Mean per-step regret)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:52:13.408Z Evaluation of model performance on the SQuAD Abstract dataset for Question Answering, specifically using the Mean per-step regret 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 | Question Answering | | Dataset (including any stated split) | SQuAD Abstract | | Metric | Mean Per-Step Regret | | Unit | SCALAR | | Direction | Lower 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 - [Mean Per-Step Regret](): Lower is better; unit: SCALAR. ## Recorded results | Method | Mean Per-Step Regret | Result date | Report paper | | --- | --- | --- | --- | | Para | 0.155 | Not recorded | 699e820b6017c4460ffacf00 | | Simpl | 0.174 | Not recorded | 699e820b6017c4460ffacf00 | | Disamb | 0.175 | Not recorded | 699e820b6017c4460ffacf00 | | LinFTPL | 0.176 | Not recorded | 699e820b6017c4460ffacf00 | | TS | 0.176 | Not recorded | 699e820b6017c4460ffacf00 | | FTPL | 0.18 | Not recorded | 699e820b6017c4460ffacf00 | | LinUCB | 0.18 | Not recorded | 699e820b6017c4460ffacf00 | | No-Rewrite (NoRw) | 0.183 | Not recorded | 699e820b6017c4460ffacf00 | | LinEXP3 | 0.183 | Not recorded | 699e820b6017c4460ffacf00 | | Clarify | 0.184 | Not recorded | 699e820b6017c4460ffacf00 | | EXP3 | 0.185 | Not recorded | 699e820b6017c4460ffacf00 | | LinUCB+KL | 0.186 | Not recorded | 699e820b6017c4460ffacf00 | | ϵ-FTRL | 0.191 | Not recorded | 699e820b6017c4460ffacf00 | | TS | 0.198 | Not recorded | 699e820b6017c4460ffacf00 | | Expand | 0.208 | Not recorded | 699e820b6017c4460ffacf00 | ### Para Mean Per-Step Regret: 0.155. Result ID: 699eaa375698665ec476702e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Static Prompts"}. This record does not assert independent reproduction. ### Simpl Mean Per-Step Regret: 0.174. Result ID: 699eaa375698665ec476702f. [Reporting paper]() Recorded evaluation configuration: {"Strategy Category":"Static Prompts"}. This record does not assert independent reproduction. ### Disamb Mean Per-Step Regret: 0.175. Result ID: 699eaa375698665ec4767030. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Static Prompts"}. This record does not assert independent reproduction. ### LinFTPL Mean Per-Step Regret: 0.176. Result ID: 699eaa375698665ec476703a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Contextual Linear"}. This record does not assert independent reproduction. ### TS Mean Per-Step Regret: 0.176. Result ID: 699eaa375698665ec476703b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Contextual Linear"}. This record does not assert independent reproduction. ### FTPL Mean Per-Step Regret: 0.18. Result ID: 699eaa375698665ec4767034. [Reporting paper]() Recorded evaluation configuration: {"Strategy Category":"Non-Contextual"}. This record does not assert independent reproduction. ### LinUCB Mean Per-Step Regret: 0.18. Result ID: 699eaa375698665ec4767037. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Contextual Linear"}. This record does not assert independent reproduction. ### No-Rewrite (NoRw) Mean Per-Step Regret: 0.183. Result ID: 699eaa375698665ec476702d. [Reporting paper]() Recorded evaluation configuration: {"Strategy Category":"Base"}. This record does not assert independent reproduction. ### LinEXP3 Mean Per-Step Regret: 0.183. Result ID: 699eaa375698665ec4767039. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Contextual Linear"}. This record does not assert independent reproduction. ### Clarify Mean Per-Step Regret: 0.184. Result ID: 699eaa375698665ec4767031. [Reporting paper]() Recorded evaluation configuration: {"Strategy Category":"Static Prompts"}. This record does not assert independent reproduction. ### EXP3 Mean Per-Step Regret: 0.185. Result ID: 699eaa375698665ec4767033. [Reporting paper]() Recorded evaluation configuration: {"Strategy Category":"Non-Contextual"}. This record does not assert independent reproduction. ### LinUCB+KL Mean Per-Step Regret: 0.186. Result ID: 699eaa375698665ec4767038. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Contextual Linear"}. This record does not assert independent reproduction. ### ϵ-FTRL Mean Per-Step Regret: 0.191. Result ID: 699eaa375698665ec4767035. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Non-Contextual"}. This record does not assert independent reproduction. ### TS Mean Per-Step Regret: 0.198. Result ID: 699eaa375698665ec4767036. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Non-Contextual"}. This record does not assert independent reproduction. ### Expand Mean Per-Step Regret: 0.208. Result ID: 699eaa375698665ec4767032. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Strategy Category":"Static Prompts"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.