# Explanation Generation on TrendFact (test) Source: [Explanation Generation on TrendFact (test)]() Collection index: [llms.txt]() Data updated: 2026-07-07T08:31:12.968Z Evaluation of the model's ability to generate textual explanations based on input data from the test split of the TrendFact dataset, measured using metrics including HCPI, ECS, BLEU-4, BERTScore, and ROUGE scores. 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 | Explanation Generation | | Dataset (including any stated split) | TrendFact (test) | | Metric | ECS | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [ECS](): Higher is better; unit: PERCENT. - [HCPI](): Higher is better; unit: PERCENT. - [BLEU-4](): Higher is better; unit: PERCENT. - [BERTScore](): Higher is better; unit: PERCENT. - [ROUGE-1](): Higher is better; unit: PERCENT. - [ROUGE-2](): Higher is better; unit: PERCENT. - [ROUGE-L](): Higher is better; unit: PERCENT. ## Recorded results | Method | ECS | Result date | Report paper | | --- | --- | --- | --- | | FactISR(QwQ-32B) | 86.1 | Not recorded | 68fa78b41e209131cea79de6 | | QwQ-32B | 85.31 | Not recorded | 68fa78b41e209131cea79de6 | | FactISR(Qwen3-32B) | 84.26 | Not recorded | 68fa78b41e209131cea79de6 | | DeepSeek-R1-0528 | 83.99 | Not recorded | 68fa78b41e209131cea79de6 | | Qwen3-32B(Think) | 83.32 | Not recorded | 68fa78b41e209131cea79de6 | | QwQ-32B-Preview | 78.43 | Not recorded | 68fa78b41e209131cea79de6 | | GPT-4.1 | 77.26 | Not recorded | 68fa78b41e209131cea79de6 | | DeepSeek-V3-0324 | 76.74 | Not recorded | 68fa78b41e209131cea79de6 | | Qwen3-32B(No think) | 75.74 | Not recorded | 68fa78b41e209131cea79de6 | | Qwen2.5-72B-instruct | 72.07 | Not recorded | 68fa78b41e209131cea79de6 | | DeepSeek-R1 | 0.9115 | Not recorded | 68fa78b41e209131cea79de6 | | o1-preview | 0.8986 | Not recorded | 68fa78b41e209131cea79de6 | | GPT-4.1 | 0.8622 | Not recorded | 68fa78b41e209131cea79de6 | | QwQ-32B-Preview | 0.8198 | Not recorded | 68fa78b41e209131cea79de6 | | DeepSeek-V3 | 0.7812 | Not recorded | 68fa78b41e209131cea79de6 | | Qwen-72B-instruct | 0.7787 | Not recorded | 68fa78b41e209131cea79de6 | ### FactISR(QwQ-32B) ECS: 86.1. Result ID: 6a4cb93660b88bb339c88ef3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### QwQ-32B ECS: 85.31. Result ID: 6a4cb93660b88bb339c88ef0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"32B"}. This record does not assert independent reproduction. ### FactISR(Qwen3-32B) ECS: 84.26. Result ID: 6a4cb93660b88bb339c88ef2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-32B"}. This record does not assert independent reproduction. ### DeepSeek-R1-0528 ECS: 83.99. Result ID: 6a4cb93660b88bb339c88ef1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"0528"}. This record does not assert independent reproduction. ### Qwen3-32B(Think) ECS: 83.32. Result ID: 6a4cb93660b88bb339c88eef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Reasoning":"enabled","Parameters":"32B"}. This record does not assert independent reproduction. ### QwQ-32B-Preview ECS: 78.43. Result ID: 6a4cb93660b88bb339c88eea. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"32B"}. This record does not assert independent reproduction. ### GPT-4.1 ECS: 77.26. Result ID: 6a4cb93660b88bb339c88eee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepSeek-V3-0324 ECS: 76.74. Result ID: 6a4cb93660b88bb339c88eed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Version":"0324"}. This record does not assert independent reproduction. ### Qwen3-32B(No think) ECS: 75.74. Result ID: 6a4cb93660b88bb339c88eec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Reasoning":"disabled","Parameters":"32B"}. This record does not assert independent reproduction. ### Qwen2.5-72B-instruct ECS: 72.07. Result ID: 6a4cb93660b88bb339c88eeb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction. ### DeepSeek-R1 ECS: 0.9115. Result ID: 6a4cb93660b88bb339c88f04. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence condition":"Gold Evidence"}. This record does not assert independent reproduction. ### o1-preview ECS: 0.8986. Result ID: 6a4cb93660b88bb339c88f05. [Reporting paper]() Recorded evaluation configuration: {"Evidence condition":"Gold Evidence"}. This record does not assert independent reproduction. ### GPT-4.1 ECS: 0.8622. Result ID: 6a4cb93660b88bb339c88f03. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence condition":"Gold Evidence"}. This record does not assert independent reproduction. ### QwQ-32B-Preview ECS: 0.8198. Result ID: 6a4cb93660b88bb339c88f00. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence condition":"Gold Evidence"}. This record does not assert independent reproduction. ### DeepSeek-V3 ECS: 0.7812. Result ID: 6a4cb93660b88bb339c88f02. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evidence condition":"Gold Evidence"}. This record does not assert independent reproduction. ### Qwen-72B-instruct ECS: 0.7787. Result ID: 6a4cb93660b88bb339c88f01. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Evidence condition":"Gold Evidence"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.