# Multi-hop Question Answering on HotpotQA (Speedup) Source: [Multi-hop Question Answering on HotpotQA (Speedup)]() Collection index: [llms.txt]() Data updated: 2026-06-02T10:16:38.231Z Evaluation of model performance on the HotpotQA dataset for multi-hop question answering, specifically reporting the inference speedup factor. 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 | Speedup Factor | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Speedup Factor](): Higher is better; unit: SCALAR. ## Recorded results | Method | Speedup Factor | Result date | Report paper | | --- | --- | --- | --- | | Hybrid Verified Decoding | 3.77 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.7 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.57 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.23 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 2.03 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 1.97 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 1.37 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 1.02 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 0.96 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 0.95 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 0.93 | Not recorded | 6a1e63fadbd7150506f85546 | | Hybrid Verified Decoding | 0.81 | Not recorded | 6a1e63fadbd7150506f85546 | ### Hybrid Verified Decoding Speedup Factor: 3.77. Result ID: 6a1ead43fbc373592c196aef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"SuffixDecoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.7. Result ID: 6a1ead43fbc373592c196af7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"SuffixDecoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.57. Result ID: 6a1ead43fbc373592c196aed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"Greedy Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.23. Result ID: 6a1ead43fbc373592c196af5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"Greedy Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 2.03. Result ID: 6a1ead43fbc373592c196af1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"Greedy Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 1.97. Result ID: 6a1ead43fbc373592c196af3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"SuffixDecoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 1.37. Result ID: 6a1ead43fbc373592c196af0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"Frequency-Based Hybrid Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 1.02. Result ID: 6a1ead43fbc373592c196af4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"Frequency-Based Hybrid Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 0.96. Result ID: 6a1ead43fbc373592c196af8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"Frequency-Based Hybrid Decoding"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 0.95. Result ID: 6a1ead43fbc373592c196aee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Reference Baseline":"EAGLE3"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 0.93. Result ID: 6a1ead43fbc373592c196af6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Llama3.1-8B","Reference Baseline":"EAGLE3"}. This record does not assert independent reproduction. ### Hybrid Verified Decoding Speedup Factor: 0.81. Result ID: 6a1ead43fbc373592c196af2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Target Model":"Qwen3-4B","Reference Baseline":"EAGLE3"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.