# Temporal Question Answering on TimeQA Hard v1 Source: [Temporal Question Answering on TimeQA Hard v1]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:59:12.831Z Evaluation of Temporal Question Answering performance on the TimeQA Hard v1 dataset, reporting ROUGE-based metrics (R-1, R-2, R-L), BLEU Score (BS), and Exact Match (EM). 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 | Temporal Question Answering | | Dataset (including any stated split) | TimeQA Hard v1 | | Metric | R-1 | | 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 - [R-1](): Higher is better; unit: SCALAR. - [R-2](): Higher is better; unit: SCALAR. - [R-L](): Higher is better; unit: SCALAR. - [BS](): Higher is better; unit: SCALAR. - [EM](): Higher is better; unit: PERCENT. ## Recorded results | Method | R-1 | Result date | Report paper | | --- | --- | --- | --- | | CoT+RL pipeline | 0.504 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | CoT+RL pipeline | 0.411 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.374 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.37 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.315 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.311 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.31 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.271 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.267 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | LoRA (r=32) | 0.246 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | SFT | 0.225 | Not recorded | 6984243ba8b01e76cc8ee8b4 | | Classifier | 0.138 | Not recorded | 6984243ba8b01e76cc8ee8b4 | ### CoT+RL pipeline R-1: 0.504. Result ID: 69964a1e5698665ec48e4eba. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type":"W/ ORIGINAL CONTEXT (C)","Model":"Qwen2.5-1.5B","Training Method":"RL"}. This record does not assert independent reproduction. ### CoT+RL pipeline R-1: 0.411. Result ID: 69964a1e5698665ec48e4eb9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Prompt Type":"W/ ORIGINAL CONTEXT (C)","Model":"Qwen2.5-0.5B","Training Method":"RL"}. This record does not assert independent reproduction. ### SFT R-1: 0.374. Result ID: 69964a1e5698665ec48e4ebc. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ TIME SUB-C","Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### SFT R-1: 0.37. Result ID: 69964a1e5698665ec48e4eb6. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ ORIGINAL CONTEXT (C)","Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### SFT R-1: 0.315. Result ID: 69964a1e5698665ec48e4eb5. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ ORIGINAL CONTEXT (C)","Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### SFT R-1: 0.311. Result ID: 69964a1e5698665ec48e4ebb. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ TIME SUB-C","Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### SFT R-1: 0.31. Result ID: 69964a1e5698665ec48e4ec0. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ KGS (WHOLE C) (FAISS)","Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### SFT R-1: 0.271. Result ID: 69964a1e5698665ec48e4ebe. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ KGS (CHUNKED C) (FAISS)","Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. ### SFT R-1: 0.267. Result ID: 69964a1e5698665ec48e4ebf. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ KGS (WHOLE C) (FAISS)","Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### LoRA (r=32) R-1: 0.246. Result ID: 69964a1e5698665ec48e4eb7. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ ORIGINAL CONTEXT (C)","Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### SFT R-1: 0.225. Result ID: 69964a1e5698665ec48e4ebd. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ KGS (CHUNKED C) (FAISS)","Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction. ### Classifier R-1: 0.138. Result ID: 69964a1e5698665ec48e4eb8. [Reporting paper]() Recorded evaluation configuration: {"Prompt Type":"W/ ORIGINAL CONTEXT (C)","Model":"Qwen2.5-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.