# E-commerce Relevance Classification on Taobao dataset (offline) Source: [E-commerce Relevance Classification on Taobao dataset (offline)]() Collection index: [llms.txt]() Data updated: 2026-03-11T08:01:25.236Z Evaluation of E-commerce Relevance Classification performance on the offline split of the Taobao dataset, reporting per-class F1 scores and overall Accuracy. 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 | E-commerce Relevance Classification | | Dataset (including any stated split) | Taobao dataset (offline) | | Metric | F1 Score (Class 1) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [F1 Score (Class 1)](): Higher is better; unit: PERCENT. - [F1 Score (Class 2)](): Higher is better; unit: PERCENT. - [F1 Score (Class 3)](): Higher is better; unit: PERCENT. - [F1 Score (Class 4)](): Higher is better; unit: PERCENT. - [Macro F1 Score](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score (Class 1) | Result date | Report paper | | --- | --- | --- | --- | | TaoSR1 | 67.34 | Not recorded | 68fa7abc1e209131cea84e67 | | TaoSR1 | 66.82 | Not recorded | 68fa7abc1e209131cea84e67 | | BERT | 65.74 | Not recorded | 68fa7abc1e209131cea84e67 | | TaoSR1 | 65.74 | Not recorded | 68fa7abc1e209131cea84e67 | | LLM-base | 65.19 | Not recorded | 68fa7abc1e209131cea84e67 | | Qwen3-30B-A3B | 65.09 | Not recorded | 68fa7abc1e209131cea84e67 | | TaoSR1 | 62.9 | Not recorded | 68fa7abc1e209131cea84e67 | | TaoSR1 | 57.63 | Not recorded | 68fa7abc1e209131cea84e67 | | TaoSR1 | 43.3 | Not recorded | 68fa7abc1e209131cea84e67 | | Qwen3-0.6B | 42.02 | Not recorded | 68fa7abc1e209131cea84e67 | ### TaoSR1 F1 Score (Class 1): 67.34. Result ID: 69b121516dbb7075b95b5557. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Stage":"CoT & DPO & GRPO","Paradigm":"post-CoT (respond-then-think)"}. This record does not assert independent reproduction. ### TaoSR1 F1 Score (Class 1): 66.82. Result ID: 69b121516dbb7075b95b5554. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Stage":"CoT & DPO & GRPO","Paradigm":"think-then-respond"}. This record does not assert independent reproduction. ### BERT F1 Score (Class 1): 65.74. Result ID: 69b121516dbb7075b95b554e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Layers":"24"}. This record does not assert independent reproduction. ### TaoSR1 F1 Score (Class 1): 65.74. Result ID: 69b121516dbb7075b95b5556. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Stage":"CoT & DPO","Paradigm":"post-CoT (respond-then-think)"}. This record does not assert independent reproduction. ### LLM-base F1 Score (Class 1): 65.19. Result ID: 69b121516dbb7075b95b5551. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-30B-A3B F1 Score (Class 1): 65.09. Result ID: 69b121516dbb7075b95b5550. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"30B-A3B"}. This record does not assert independent reproduction. ### TaoSR1 F1 Score (Class 1): 62.9. Result ID: 69b121516dbb7075b95b5553. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Stage":"CoT & DPO","Paradigm":"think-then-respond"}. This record does not assert independent reproduction. ### TaoSR1 F1 Score (Class 1): 57.63. Result ID: 69b121516dbb7075b95b5555. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Stage":"CoT","Paradigm":"post-CoT (respond-then-think)"}. This record does not assert independent reproduction. ### TaoSR1 F1 Score (Class 1): 43.3. Result ID: 69b121516dbb7075b95b5552. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Stage":"CoT","Paradigm":"think-then-respond"}. This record does not assert independent reproduction. ### Qwen3-0.6B F1 Score (Class 1): 42.02. Result ID: 69b121516dbb7075b95b554f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"0.6B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.