# Multi-hop Question Answering on MuSiQue (EM, ASR) Source: [Multi-hop Question Answering on MuSiQue (EM, ASR)]() Collection index: [llms.txt]() Data updated: 2026-07-02T08:40:29.168Z Evaluation of model performance on the MuSiQue dataset for Multi-hop Question Answering, reporting Exact Match (EM) and Answer Selection Rate (ASR). 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 | Multi-hop Question Answering | | Dataset (including any stated split) | MuSiQue | | Metric | Exact Match (EM) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Exact Match (EM)](): Higher is better; unit: PERCENT. - [Answer Selection Rate (ASR)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Exact Match (EM) | Result date | Report paper | | --- | --- | --- | --- | | Clean (No Attack) | 38 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 36 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 35 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 32 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 28 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 28 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 26 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 23 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 22 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 22 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 21 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 20 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 19 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 19 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 19 | Not recorded | 6a45f087dc71372d7795a25c | | Naive | 18 | Not recorded | 6a45f087dc71372d7795a25c | | PARADOX | 18 | Not recorded | 6a45f087dc71372d7795a25c | | Clean (No Attack) | 17 | Not recorded | 6a45f087dc71372d7795a25c | | Ignore | 16 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 16 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 13 | Not recorded | 6a45f087dc71372d7795a25c | | Combined | 9 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 8 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 8 | Not recorded | 6a45f087dc71372d7795a25c | | PoisonedRAG | 8 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 8 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 7 | Not recorded | 6a45f087dc71372d7795a25c | | KidnapRAG | 1 | Not recorded | 6a45f087dc71372d7795a25c | ### Clean (No Attack) Exact Match (EM): 38. Result ID: 6a4623fb60b88bb33985411b. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PARADOX Exact Match (EM): 36. Result ID: 6a4623fb60b88bb339854120. [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 Exact Match (EM): 35. Result ID: 6a4623fb60b88bb339854119. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Clean (No Attack) Exact Match (EM): 32. Result ID: 6a4623fb60b88bb339854114. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Naive Exact Match (EM): 28. Result ID: 6a4623fb60b88bb33985411c. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### PARADOX Exact Match (EM): 28. Result ID: 6a4623fb60b88bb339854127. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Naive Exact Match (EM): 26. Result ID: 6a4623fb60b88bb339854123. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Clean (No Attack) Exact Match (EM): 23. Result ID: 6a4623fb60b88bb339854122. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Ignore Exact Match (EM): 22. Result ID: 6a4623fb60b88bb339854116. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Ignore Exact Match (EM): 22. Result ID: 6a4623fb60b88bb339854124. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Naive Exact Match (EM): 21. Result ID: 6a4623fb60b88bb33985412a. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### PoisonedRAG Exact Match (EM): 20. Result ID: 6a4623fb60b88bb33985411f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Combined Exact Match (EM): 19. Result ID: 6a4623fb60b88bb339854125. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### Ignore Exact Match (EM): 19. Result ID: 6a4623fb60b88bb33985412b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Combined Exact Match (EM): 19. Result ID: 6a4623fb60b88bb33985412c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Naive Exact Match (EM): 18. Result ID: 6a4623fb60b88bb339854115. [Reporting paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### PARADOX Exact Match (EM): 18. Result ID: 6a4623fb60b88bb33985412e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Clean (No Attack) Exact Match (EM): 17. Result ID: 6a4623fb60b88bb339854129. [Reporting paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### Ignore Exact Match (EM): 16. Result ID: 6a4623fb60b88bb33985411d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Llama-3.3-70B-Inst"}. This record does not assert independent reproduction. ### Combined Exact Match (EM): 16. Result ID: 6a4623fb60b88bb33985411e. [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 Exact Match (EM): 13. Result ID: 6a4623fb60b88bb339854118. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### Combined Exact Match (EM): 9. Result ID: 6a4623fb60b88bb339854117. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### KidnapRAG Exact Match (EM): 8. Result ID: 6a4623fb60b88bb33985411a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"ReAct","LLM Backbone":"Qwen2.5-32B-Inst"}. This record does not assert independent reproduction. ### PoisonedRAG Exact Match (EM): 8. Result ID: 6a4623fb60b88bb339854126. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### PoisonedRAG Exact Match (EM): 8. Result ID: 6a4623fb60b88bb33985412d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### KidnapRAG Exact Match (EM): 8. Result ID: 6a4623fb60b88bb33985412f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"DeepSeek-32B"}. This record does not assert independent reproduction. ### KidnapRAG Exact Match (EM): 7. Result ID: 6a4623fb60b88bb339854128. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Framework":"WebThinker","LLM Backbone":"QwQ-32B"}. This record does not assert independent reproduction. ### KidnapRAG Exact Match (EM): 1. Result ID: 6a4623fb60b88bb339854121. [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.