# Question Answering on 2WikiMultihopQA (EM/ASR) Source: [Question Answering on 2WikiMultihopQA (EM/ASR)]() Collection index: [llms.txt]() Data updated: 2026-07-02T08:40:29.285Z Evaluation of Question Answering performance on the 2WikiMultihopQA dataset, reporting Exact Match (EM) and Accuracy/Success Rate (ASR) 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 | Question Answering | | Dataset (including any stated split) | 2WikiMultihopQA | | Metric | EM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 36 of 36 | | 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 - [EM](): Higher is better; unit: PERCENT. - [ASR](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | Clean (No Attack) | 60 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 59 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 59 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 58 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 58 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 58 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 57 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 56 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 55 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 54 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 54 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 53 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 51 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 51 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 49 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 48 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 47 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 41 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 41 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 38 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 37 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 37 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 36 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 35 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 34 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 34 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 34 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 29 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 26 | Not recorded | 6a45f087dc71372d7795a25c | | Fake Completion | 24 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 24 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 20 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 18 | Not recorded | 6a45f087dc71372d7795a25c | | Topic | 15 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 9 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 9 | Not recorded | 6a45f087dc71372d7795a25c | ### Clean (No Attack) EM: 60. Result ID: 6a4623fb60b88bb3398541a0. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Ignore EM: 59. Result ID: 6a4623fb60b88bb3398541b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Ignore EM: 59. Result ID: 6a4623fb60b88bb3398541bd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Clean (No Attack) EM: 58. Result ID: 6a4623fb60b88bb3398541bb. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Combined EM: 58. Result ID: 6a4623fb60b88bb3398541bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Topic EM: 58. Result ID: 6a4623fb60b88bb3398541c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Clean (No Attack) EM: 57. Result ID: 6a4623fb60b88bb3398541b2. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Naive EM: 56. Result ID: 6a4623fb60b88bb3398541b3. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Naive EM: 55. Result ID: 6a4623fb60b88bb3398541bc. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Clean (No Attack) EM: 54. Result ID: 6a4623fb60b88bb3398541a9. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Topic EM: 54. Result ID: 6a4623fb60b88bb3398541b7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Combined EM: 53. Result ID: 6a4623fb60b88bb3398541b6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### PARADOX EM: 51. Result ID: 6a4623fb60b88bb3398541b9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Fake Completion EM: 51. Result ID: 6a4623fb60b88bb3398541be. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Fake Completion EM: 49. Result ID: 6a4623fb60b88bb3398541ac. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Fake Completion EM: 48. Result ID: 6a4623fb60b88bb3398541b5. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Naive EM: 47. Result ID: 6a4623fb60b88bb3398541aa. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 41. Result ID: 6a4623fb60b88bb3398541af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PARADOX EM: 41. Result ID: 6a4623fb60b88bb3398541b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PARADOX EM: 38. Result ID: 6a4623fb60b88bb3398541c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Naive EM: 37. Result ID: 6a4623fb60b88bb3398541a1. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 37. Result ID: 6a4623fb60b88bb3398541a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### PARADOX EM: 36. Result ID: 6a4623fb60b88bb3398541a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 35. Result ID: 6a4623fb60b88bb3398541c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Ignore EM: 34. Result ID: 6a4623fb60b88bb3398541a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Combined EM: 34. Result ID: 6a4623fb60b88bb3398541ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PoisonedRAG EM: 34. Result ID: 6a4623fb60b88bb3398541b8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### KidnapRAG EM: 29. Result ID: 6a4623fb60b88bb3398541ba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Combined EM: 26. Result ID: 6a4623fb60b88bb3398541a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Fake Completion EM: 24. Result ID: 6a4623fb60b88bb3398541a3. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Ignore EM: 24. Result ID: 6a4623fb60b88bb3398541ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### KidnapRAG EM: 20. Result ID: 6a4623fb60b88bb3398541c3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Topic EM: 18. Result ID: 6a4623fb60b88bb3398541ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Topic EM: 15. Result ID: 6a4623fb60b88bb3398541a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### KidnapRAG EM: 9. Result ID: 6a4623fb60b88bb3398541a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### KidnapRAG EM: 9. Result ID: 6a4623fb60b88bb3398541b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.