# Inter-Context Knowledge Conflict on StrategyQA Source: [Inter-Context Knowledge Conflict on StrategyQA]() Collection index: [llms.txt]() Data updated: 2026-07-01T07:46:48.241Z Evaluation of model performance on the StrategyQA dataset focusing on resolving inter-context knowledge conflicts, measured using ACCL, ACCEM, and ACCCEM metrics. 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 | Inter-Context Knowledge Conflict | | Dataset (including any stated split) | strategyQA | | Metric | ACCL | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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 - [ACCL](): Higher is better; unit: PERCENT. - [ACCEM](): Higher is better; unit: PERCENT. - [ACCCEM](): Higher is better; unit: PERCENT. ## Recorded results | Method | ACCL | Result date | Report paper | | --- | --- | --- | --- | | KCR (“Text”) | 83.2 | Not recorded | 68fa7a621e209131cea82c1f | | KCR (“Graph”) | 82.4 | Not recorded | 68fa7a621e209131cea82c1f | | KCR (“Text”) | 77.6 | Not recorded | 68fa7a621e209131cea82c1f | | Qwen 3-8B (Thinking) | 76 | Not recorded | 68fa7a621e209131cea82c1f | | KCR (“Graph”) | 75.2 | Not recorded | 68fa7a621e209131cea82c1f | | GPT-4o-mini | 74.4 | Not recorded | 68fa7a621e209131cea82c1f | | Qwen 2.5-7B | 68.8 | Not recorded | 68fa7a621e209131cea82c1f | | GPT-5.1 (Thinking) | 66.4 | Not recorded | 68fa7a621e209131cea82c1f | | KCR (“Text”) | 64 | Not recorded | 68fa7a621e209131cea82c1f | | ASTUTE RAG (GPT-4o) | 59.2 | Not recorded | 68fa7a621e209131cea82c1f | | Directly Use Backbone | 59.2 | Not recorded | 68fa7a621e209131cea82c1f | | KCR (“Text”) | 58.61 | Not recorded | 68fa7a621e209131cea82c1f | | ASTUTE RAG (GPT-5.1) | 57.6 | Not recorded | 68fa7a621e209131cea82c1f | | Directly Use Backbone | 56 | Not recorded | 68fa7a621e209131cea82c1f | | KCR (“Graph”) | 56 | Not recorded | 68fa7a621e209131cea82c1f | | Qwen 2.5-3B | 54.4 | Not recorded | 68fa7a621e209131cea82c1f | | Directly Use Backbone | 53.6 | Not recorded | 68fa7a621e209131cea82c1f | | KCR (“Graph”) | 52.78 | Not recorded | 68fa7a621e209131cea82c1f | | Directly Use Backbone | 51.2 | Not recorded | 68fa7a621e209131cea82c1f | | Qwen 2.5-1.5B | 50.4 | Not recorded | 68fa7a621e209131cea82c1f | | CUAD (Default) | 50.4 | Not recorded | 68fa7a621e209131cea82c1f | | ADACAD (Default) | 50.4 | Not recorded | 68fa7a621e209131cea82c1f | | COCOA (Default) | 50.4 | Not recorded | 68fa7a621e209131cea82c1f | | ASTUTE RAG | 50.4 | Not recorded | 68fa7a621e209131cea82c1f | | Llama 3.2-3B | 46.4 | Not recorded | 68fa7a621e209131cea82c1f | | CAD Decoding | 46.4 | Not recorded | 68fa7a621e209131cea82c1f | | ASTUTE RAG | 46.4 | Not recorded | 68fa7a621e209131cea82c1f | | Llama 3.2-1B | 44.8 | Not recorded | 68fa7a621e209131cea82c1f | | Llama 3.1-8B | 44.8 | Not recorded | 68fa7a621e209131cea82c1f | | ASTUTE RAG | 36.8 | Not recorded | 68fa7a621e209131cea82c1f | | CAD Decoding | 31.2 | Not recorded | 68fa7a621e209131cea82c1f | | CAD Decoding | 31.2 | Not recorded | 68fa7a621e209131cea82c1f | ### KCR (“Text”) ACCL: 83.2. Result ID: 6a44c5e773d097d845beb6f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5-7B","Format":"Text"}. This record does not assert independent reproduction. ### KCR (“Graph”) ACCL: 82.4. Result ID: 6a44c5e773d097d845beb6ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.2-3B","Format":"Graph"}. This record does not assert independent reproduction. ### KCR (“Text”) ACCL: 77.6. Result ID: 6a44c5e773d097d845beb6ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.2-3B","Format":"Text"}. This record does not assert independent reproduction. ### Qwen 3-8B (Thinking) ACCL: 76. Result ID: 6a44c5e773d097d845beb6df. [Reporting paper]() Recorded evaluation configuration: {"Model Family":"Direct Generation (Without Context)"}. This record does not assert independent reproduction. ### KCR (“Graph”) ACCL: 75.2. Result ID: 6a44c5e773d097d845beb6f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5-7B","Format":"Graph"}. This record does not assert independent reproduction. ### GPT-4o-mini ACCL: 74.4. Result ID: 6a44c5e773d097d845beb6e0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Family":"Direct Generation (Without Context)"}. This record does not assert independent reproduction. ### Qwen 2.5-7B ACCL: 68.8. Result ID: 6a44c5e773d097d845beb6de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"Direct Generation (Without Context)"}. This record does not assert independent reproduction. ### GPT-5.1 (Thinking) ACCL: 66.4. Result ID: 6a44c5e773d097d845beb6e1. [Reporting paper]() Recorded evaluation configuration: {"Model Family":"Direct Generation (Without Context)"}. This record does not assert independent reproduction. ### KCR (“Text”) ACCL: 64. Result ID: 6a44c5e773d097d845beb6f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B (Thinking)","Format":"Text"}. This record does not assert independent reproduction. ### ASTUTE RAG (GPT-4o) ACCL: 59.2. Result ID: 6a44c5e773d097d845beb6e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### Directly Use Backbone ACCL: 59.2. Result ID: 6a44c5e773d097d845beb6f0. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5-7B"}. This record does not assert independent reproduction. ### KCR (“Text”) ACCL: 58.61. Result ID: 6a44c5e773d097d845beb6fb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B","Format":"Text"}. This record does not assert independent reproduction. ### ASTUTE RAG (GPT-5.1) ACCL: 57.6. Result ID: 6a44c5e773d097d845beb6ea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### Directly Use Backbone ACCL: 56. Result ID: 6a44c5e773d097d845beb6f5. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B (Thinking)"}. This record does not assert independent reproduction. ### KCR (“Graph”) ACCL: 56. Result ID: 6a44c5e773d097d845beb6f7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B (Thinking)","Format":"Graph"}. This record does not assert independent reproduction. ### Qwen 2.5-3B ACCL: 54.4. Result ID: 6a44c5e773d097d845beb6e5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### Directly Use Backbone ACCL: 53.6. Result ID: 6a44c5e773d097d845beb6f8. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B"}. This record does not assert independent reproduction. ### KCR (“Graph”) ACCL: 52.78. Result ID: 6a44c5e773d097d845beb6fc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B","Format":"Graph"}. This record does not assert independent reproduction. ### Directly Use Backbone ACCL: 51.2. Result ID: 6a44c5e773d097d845beb6eb. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.2-3B"}. This record does not assert independent reproduction. ### Qwen 2.5-1.5B ACCL: 50.4. Result ID: 6a44c5e773d097d845beb6e4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### CUAD (Default) ACCL: 50.4. Result ID: 6a44c5e773d097d845beb6e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### ADACAD (Default) ACCL: 50.4. Result ID: 6a44c5e773d097d845beb6e7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### COCOA (Default) ACCL: 50.4. Result ID: 6a44c5e773d097d845beb6e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### ASTUTE RAG ACCL: 50.4. Result ID: 6a44c5e773d097d845beb6fa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B"}. This record does not assert independent reproduction. ### Llama 3.2-3B ACCL: 46.4. Result ID: 6a44c5e773d097d845beb6dd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Family":"Direct Generation (Without Context)"}. This record does not assert independent reproduction. ### CAD Decoding ACCL: 46.4. Result ID: 6a44c5e773d097d845beb6ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.2-3B"}. This record does not assert independent reproduction. ### ASTUTE RAG ACCL: 46.4. Result ID: 6a44c5e773d097d845beb6ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama 3.2-3B"}. This record does not assert independent reproduction. ### Llama 3.2-1B ACCL: 44.8. Result ID: 6a44c5e773d097d845beb6e2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### Llama 3.1-8B ACCL: 44.8. Result ID: 6a44c5e773d097d845beb6e3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Model Family":"General Baselines (With Context)"}. This record does not assert independent reproduction. ### ASTUTE RAG ACCL: 36.8. Result ID: 6a44c5e773d097d845beb6f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5-7B"}. This record does not assert independent reproduction. ### CAD Decoding ACCL: 31.2. Result ID: 6a44c5e773d097d845beb6f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 2.5-7B"}. This record does not assert independent reproduction. ### CAD Decoding ACCL: 31.2. Result ID: 6a44c5e773d097d845beb6f9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen 3-8B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.