# Debate Stance Prediction on ExplaGraphs (test) Source: [Debate Stance Prediction on ExplaGraphs (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:55.561Z Evaluation of models performing Debate Stance Prediction on the test split of the ExplaGraphs dataset, typically measured using 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 | Debate Stance Prediction | | Dataset (including any stated split) | ExplaGraphs (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | NAG-LoRA | 82.49 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenE | 80.51 | Not recorded | 69802f69a8b01e76cc8e14e4 | | NAG-Zero | 78.16 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenN | 70.94 | Not recorded | 69802f69a8b01e76cc8e14e4 | | GraphTokenG | 65.52 | Not recorded | 69802f69a8b01e76cc8e14e4 | | Qwen3-LoRA | 62.09 | Not recorded | 69802f69a8b01e76cc8e14e4 | | Qwen3-Direct | 58.84 | Not recorded | 69802f69a8b01e76cc8e14e4 | ### NAG-LoRA Accuracy: 82.49. Result ID: 69965d0f5698665ec4a2c3d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Evaluation Protocol":"LoRA Fine-tuning"}. This record does not assert independent reproduction. ### GraphTokenE Accuracy: 80.51. Result ID: 69965d0f5698665ec4a2c3d2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Granularity":"Edge-level"}. This record does not assert independent reproduction. ### NAG-Zero Accuracy: 78.16. Result ID: 69965d0f5698665ec4a2c3d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Evaluation Protocol":"Lightweight Adapter Training"}. This record does not assert independent reproduction. ### GraphTokenN Accuracy: 70.94. Result ID: 69965d0f5698665ec4a2c3d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Granularity":"Node-level"}. This record does not assert independent reproduction. ### GraphTokenG Accuracy: 65.52. Result ID: 69965d0f5698665ec4a2c3d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Granularity":"Graph-level"}. This record does not assert independent reproduction. ### Qwen3-LoRA Accuracy: 62.09. Result ID: 69965d0f5698665ec4a2c3cf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Evaluation Protocol":"LoRA Fine-tuning"}. This record does not assert independent reproduction. ### Qwen3-Direct Accuracy: 58.84. Result ID: 69965d0f5698665ec4a2c3ce. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-600M","Evaluation Protocol":"Direct Text-only Inference"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.