# Personalized Generation on PersonaMem 32K memory corpus 1.0 (test) Source: [Personalized Generation on PersonaMem 32K memory corpus 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-03-11T08:24:37.480Z Evaluation of Personalized Generation performance on the test split of the PersonaMem 32K memory corpus 1.0 dataset, assessing metrics related to memory tracking (Track Evolution, Shared Facts), preference alignment (Latest Prefs, Aligned Recs), and novelty (New Ideas, New Scenarios). 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 | Personalized Generation | | Dataset (including any stated split) | PersonaMem 32K memory corpus 1.0 (test) | | Metric | Revisit Reasons | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | 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 - [Revisit Reasons](): Higher is better; unit: PERCENT. - [Track Evolution](): Higher is better; unit: PERCENT. - [Latest Prefs](): Higher is better; unit: PERCENT. - [Aligned Recs](): Higher is better; unit: PERCENT. - [New Scenarios](): Higher is better; unit: PERCENT. - [Shared Facts](): Higher is better; unit: PERCENT. - [New Ideas](): Higher is better; unit: PERCENT. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Revisit Reasons | Result date | Report paper | | --- | --- | --- | --- | | Recol. | 94.95 | Not recorded | 69b0f7232d603e6de3e45e87 | | RF-Mem | 94.95 | Not recorded | 69b0f7232d603e6de3e45e87 | | Full Context | 93.94 | Not recorded | 69b0f7232d603e6de3e45e87 | | Dense Retrieval | 90.91 | Not recorded | 69b0f7232d603e6de3e45e87 | | Zero Memory | 72.73 | Not recorded | 69b0f7232d603e6de3e45e87 | ### Recol. Revisit Reasons: 94.95. Result ID: 69b126c16dbb7075b95b8234. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Retri Time":"7.09ms","Avg. Tokens":"3711.1"}. This record does not assert independent reproduction. ### RF-Mem Revisit Reasons: 94.95. Result ID: 69b126c16dbb7075b95b8235. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Retri Time":"5.09ms","Avg. Tokens":"3566.6"}. This record does not assert independent reproduction. ### Full Context Revisit Reasons: 93.94. Result ID: 69b126c16dbb7075b95b8232. [Reporting paper]() Recorded evaluation configuration: {"Retri Time":"NA","Avg. Tokens":"24657.8"}. This record does not assert independent reproduction. ### Dense Retrieval Revisit Reasons: 90.91. Result ID: 69b126c16dbb7075b95b8233. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Retri Time":"3.14ms","Avg. Tokens":"3515.9"}. This record does not assert independent reproduction. ### Zero Memory Revisit Reasons: 72.73. Result ID: 69b126c16dbb7075b95b8231. [Reporting paper]() Recorded evaluation configuration: {"Retri Time":"NA","Avg. Tokens":"464.6"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.