# Tampered Text Classification on TFR CTM Cross-Method Source: [Tampered Text Classification on TFR CTM Cross-Method]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:33:22.261Z Evaluation of Tampered Text Classification performance on the TFR CTM Cross-Method dataset, measured using Accuracy. 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 | Tampered Text Classification | | Dataset (including any stated split) | TFR CTM Cross-Method | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | TextShield-R1 | 88.8 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-7B | 73.6 | Not recorded | 699d30aa6017c4460ffab609 | | FakeShield\* | 73.6 | Not recorded | 699d30aa6017c4460ffab609 | | SIDA\* | 73.6 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-8B | 67.7 | Not recorded | 699d30aa6017c4460ffab609 | | MiniCPM\_V\_2.6 | 64.8 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-3B | 63 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-2B | 62.5 | Not recorded | 699d30aa6017c4460ffab609 | | FakeShield | 57.5 | Not recorded | 699d30aa6017c4460ffab609 | | SIDA | 57.5 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-3B | 42.2 | Not recorded | 699d30aa6017c4460ffab609 | | GPT4o | 37.8 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-7B | 34 | Not recorded | 699d30aa6017c4460ffab609 | | MiniCPM\_V\_2.6 | 26.2 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-8B | 25.2 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-2B | 20.3 | Not recorded | 699d30aa6017c4460ffab609 | ### TextShield-R1 Accuracy: 88.8. Result ID: 699e56415698665ec4166314. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy: 73.6. Result ID: 699e56415698665ec416630f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### FakeShield\* Accuracy: 73.6. Result ID: 699e56415698665ec4166311. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images","Base MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### SIDA\* Accuracy: 73.6. Result ID: 699e56415698665ec4166313. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images","Base MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### InternVL3-8B Accuracy: 67.7. Result ID: 699e56415698665ec416630d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### MiniCPM\_V\_2.6 Accuracy: 64.8. Result ID: 699e56415698665ec416630b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Accuracy: 63. Result ID: 699e56415698665ec416630e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### InternVL3-2B Accuracy: 62.5. Result ID: 699e56415698665ec416630c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### FakeShield Accuracy: 57.5. Result ID: 699e56415698665ec4166310. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### SIDA Accuracy: 57.5. Result ID: 699e56415698665ec4166312. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Accuracy: 42.2. Result ID: 699e56415698665ec4166309. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### GPT4o Accuracy: 37.8. Result ID: 699e56415698665ec4166305. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Accuracy: 34. Result ID: 699e56415698665ec416630a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### MiniCPM\_V\_2.6 Accuracy: 26.2. Result ID: 699e56415698665ec4166306. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### InternVL3-8B Accuracy: 25.2. Result ID: 699e56415698665ec4166308. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### InternVL3-2B Accuracy: 20.3. Result ID: 699e56415698665ec4166307. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.