# Knowledge Base Question Answering on SPICE (test) Source: [Knowledge Base Question Answering on SPICE (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:09:19.507Z Evaluation of Knowledge Base Question Answering performance on the test split of the SPICE dataset, focusing on detailed reasoning metrics (m-F1 and AC). 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 | Knowledge Base Question Answering | | Dataset (including any stated split) | SPICE (test) | | Metric | m-F1 (Logical Reasoning) | | 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 - [m-F1 (Logical Reasoning)](): Higher is better; unit: PERCENT. - [m-F1 (Quantitative Reasoning)](): Higher is better; unit: PERCENT. - [m-F1 (Comparative Reasoning)](): Higher is better; unit: PERCENT. - [m-F1 (Simple Question - Coref)](): Higher is better; unit: PERCENT. - [m-F1 (Simple Question - Direct)](): Higher is better; unit: PERCENT. - [m-F1 (Simple Question - Ellipsis)](): Higher is better; unit: PERCENT. - [AC (Verification - Boolean)](): Higher is better; unit: PERCENT. - [AC (Quantitative Reasoning - Count)](): Higher is better; unit: PERCENT. - [AC (Comparative Reasoning - Count)](): Higher is better; unit: PERCENT. - [Overall AC](): Higher is better; unit: PERCENT. ## Recorded results | Method | m-F1 (Logical Reasoning) | Result date | Report paper | | --- | --- | --- | --- | | LLM\_GT | 89.61 | Not recorded | 6932670bd6b0dd33429342bd | | SEAL | 73.08 | Not recorded | 6932670bd6b0dd33429342bd | | DCG\_GL | 54.21 | Not recorded | 6932670bd6b0dd33429342bd | | KB-Binder | 46.85 | Not recorded | 6932670bd6b0dd33429342bd | | BertSP\_GL | 24.08 | Not recorded | 6932670bd6b0dd33429342bd | ### LLM\_GT m-F1 (Logical Reasoning): 89.61. Result ID: 6996cc315698665ec4180bae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Setting":"Unsupervised"}. This record does not assert independent reproduction. ### SEAL m-F1 (Logical Reasoning): 73.08. Result ID: 6996cc315698665ec4180bb0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Setting":"Unsupervised"}. This record does not assert independent reproduction. ### DCG\_GL m-F1 (Logical Reasoning): 54.21. Result ID: 6996cc315698665ec4180bac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Setting":"Supervised"}. This record does not assert independent reproduction. ### KB-Binder m-F1 (Logical Reasoning): 46.85. Result ID: 6996cc315698665ec4180baf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Setting":"Unsupervised"}. This record does not assert independent reproduction. ### BertSP\_GL m-F1 (Logical Reasoning): 24.08. Result ID: 6996cc315698665ec4180bad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Learning Setting":"Supervised"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.