# Explanation Refinement on EntailmentBank Source: [Explanation Refinement on EntailmentBank]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:47:13.208Z Evaluation of model performance on the Explanation Refinement task using the EntailmentBank dataset, measured by initial and final 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 Refinement | | Dataset (including any stated split) | EntailmentBank | | Metric | Initial Score | | Unit | PERCENT | | Direction | Higher 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 - [Initial Score](): Higher is better; unit: PERCENT. - [Final Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Initial Score | Result date | Report paper | | --- | --- | --- | --- | | Faithful-Refiner | 25.33 | Not recorded | 69799852a2b28e761d87cd73 | | Faithful-Refiner | 23.33 | Not recorded | 69799852a2b28e761d87cd73 | | LLM-TP Tree | 22.67 | Not recorded | 69799852a2b28e761d87cd73 | | LLM-TP Tree | 22 | Not recorded | 69799852a2b28e761d87cd73 | | Faithful-Refiner | 22 | Not recorded | 69799852a2b28e761d87cd73 | | LLM-TP Tree | 21.33 | Not recorded | 69799852a2b28e761d87cd73 | | LLM-TP Tree | 18 | Not recorded | 69799852a2b28e761d87cd73 | | Faithful-Refiner | 17.33 | Not recorded | 69799852a2b28e761d87cd73 | | LLM-TP Tree | 16.67 | Not recorded | 69799852a2b28e761d87cd73 | | Explanation-Refiner | 16.67 | Not recorded | 69799852a2b28e761d87cd73 | | Explanation-Refiner | 15.33 | Not recorded | 69799852a2b28e761d87cd73 | | Explanation-Refiner | 15.33 | Not recorded | 69799852a2b28e761d87cd73 | | Faithful-Refiner | 14 | Not recorded | 69799852a2b28e761d87cd73 | | Explanation-Refiner | 12 | Not recorded | 69799852a2b28e761d87cd73 | | Explanation-Refiner | 8.67 | Not recorded | 69799852a2b28e761d87cd73 | ### Faithful-Refiner Initial Score: 25.33. Result ID: 699668a45698665ec4af2aa0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.1"}. This record does not assert independent reproduction. ### Faithful-Refiner Initial Score: 23.33. Result ID: 699668a45698665ec4af2a97. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction. ### LLM-TP Tree Initial Score: 22.67. Result ID: 699668a45698665ec4af2aa4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-max"}. This record does not assert independent reproduction. ### LLM-TP Tree Initial Score: 22. Result ID: 699668a45698665ec4af2aa1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.1"}. This record does not assert independent reproduction. ### Faithful-Refiner Initial Score: 22. Result ID: 699668a45698665ec4af2aa3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-max"}. This record does not assert independent reproduction. ### LLM-TP Tree Initial Score: 21.33. Result ID: 699668a45698665ec4af2a98. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction. ### LLM-TP Tree Initial Score: 18. Result ID: 699668a45698665ec4af2a9b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-5 nano"}. This record does not assert independent reproduction. ### Faithful-Refiner Initial Score: 17.33. Result ID: 699668a45698665ec4af2a9a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-5 nano"}. This record does not assert independent reproduction. ### LLM-TP Tree Initial Score: 16.67. Result ID: 699668a45698665ec4af2a9e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Grok-4 fast"}. This record does not assert independent reproduction. ### Explanation-Refiner Initial Score: 16.67. Result ID: 699668a45698665ec4af2aa2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-max"}. This record does not assert independent reproduction. ### Explanation-Refiner Initial Score: 15.33. Result ID: 699668a45698665ec4af2a96. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o"}. This record does not assert independent reproduction. ### Explanation-Refiner Initial Score: 15.33. Result ID: 699668a45698665ec4af2a9f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Deepseek-V3.1"}. This record does not assert independent reproduction. ### Faithful-Refiner Initial Score: 14. Result ID: 699668a45698665ec4af2a9d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Grok-4 fast"}. This record does not assert independent reproduction. ### Explanation-Refiner Initial Score: 12. Result ID: 699668a45698665ec4af2a99. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-5 nano"}. This record does not assert independent reproduction. ### Explanation-Refiner Initial Score: 8.67. Result ID: 699668a45698665ec4af2a9c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Grok-4 fast"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.