# Multi-Hop Question Answering on HotpotQA (EM, F1aware) Source: [Multi-Hop Question Answering on HotpotQA (EM, F1aware)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:38.834Z Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, reporting Exact Match (EM) and F1aware 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 | Multi-Hop Question Answering | | Dataset (including any stated split) | HotpotQA | | Metric | EM | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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. - [F1aware](): Higher is better; unit: PERCENT. ## Recorded results | Method | EM | Result date | Report paper | | --- | --- | --- | --- | | Search-R1 | 38.2 | Not recorded | 6944dc29423ea42265729cf9 | | Search-R1 | 36.9 | Not recorded | 6944dc29423ea42265729cf9 | | ADASEARCH | 34.4 | Not recorded | 6944dc29423ea42265729cf9 | | Awareness Shaping | 33.7 | Not recorded | 6944dc29423ea42265729cf9 | | ADASEARCH | 33.4 | Not recorded | 6944dc29423ea42265729cf9 | | IKEA | 32.3 | Not recorded | 6944dc29423ea42265729cf9 | | Awareness Shaping | 32.1 | Not recorded | 6944dc29423ea42265729cf9 | | IKEA | 32 | Not recorded | 6944dc29423ea42265729cf9 | | Naive Shaping | 31.2 | Not recorded | 6944dc29423ea42265729cf9 | | Naive Shaping | 29.8 | Not recorded | 6944dc29423ea42265729cf9 | | RAG | 24.6 | Not recorded | 6944dc29423ea42265729cf9 | | RL w/o search | 23.7 | Not recorded | 6944dc29423ea42265729cf9 | | RAG | 20.6 | Not recorded | 6944dc29423ea42265729cf9 | | RL w/o search | 20.5 | Not recorded | 6944dc29423ea42265729cf9 | | CoT | 17.3 | Not recorded | 6944dc29423ea42265729cf9 | | CoT | 16.3 | Not recorded | 6944dc29423ea42265729cf9 | | Direct Answer | 13.2 | Not recorded | 6944dc29423ea42265729cf9 | | Direct Answer | 12.5 | Not recorded | 6944dc29423ea42265729cf9 | ### Search-R1 EM: 38.2. Result ID: 6996b9bb5698665ec40471f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### Search-R1 EM: 36.9. Result ID: 6996b9bb5698665ec40471e9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### ADASEARCH EM: 34.4. Result ID: 6996b9bb5698665ec40471f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Paper Method"}. This record does not assert independent reproduction. ### Awareness Shaping EM: 33.7. Result ID: 6996b9bb5698665ec40471f4. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### ADASEARCH EM: 33.4. Result ID: 6996b9bb5698665ec40471ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Paper Method"}. This record does not assert independent reproduction. ### IKEA EM: 32.3. Result ID: 6996b9bb5698665ec40471f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### Awareness Shaping EM: 32.1. Result ID: 6996b9bb5698665ec40471eb. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### IKEA EM: 32. Result ID: 6996b9bb5698665ec40471ec. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### Naive Shaping EM: 31.2. Result ID: 6996b9bb5698665ec40471f3. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### Naive Shaping EM: 29.8. Result ID: 6996b9bb5698665ec40471ea. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Reward-Shaping Baselines"}. This record does not assert independent reproduction. ### RAG EM: 24.6. Result ID: 6996b9bb5698665ec40471e7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### RL w/o search EM: 23.7. Result ID: 6996b9bb5698665ec40471f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### RAG EM: 20.6. Result ID: 6996b9bb5698665ec40471f0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### RL w/o search EM: 20.5. Result ID: 6996b9bb5698665ec40471e8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Outcome RL Baselines"}. This record does not assert independent reproduction. ### CoT EM: 17.3. Result ID: 6996b9bb5698665ec40471e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### CoT EM: 16.3. Result ID: 6996b9bb5698665ec40471ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### Direct Answer EM: 13.2. Result ID: 6996b9bb5698665ec40471e5. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Qwen2.5-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. ### Direct Answer EM: 12.5. Result ID: 6996b9bb5698665ec40471ee. [Reporting paper]() Recorded evaluation configuration: {"Base Model":"Llama-3.2-3B-Instruct","Category":"Prompting Baselines"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.