# Cross-lingual Aspect-Based Sentiment Analysis on Multilingual ABSA (M-ABSA) (test) Source: [Cross-lingual Aspect-Based Sentiment Analysis on Multilingual ABSA (M-ABSA) (test)]() Collection index: [llms.txt]() Data updated: 2026-04-13T09:40:14.445Z Evaluation of Cross-lingual Aspect-Based Sentiment Analysis performance on the M-ABSA test set, reporting metrics across French (FR), Spanish (ES), Dutch (NL), Russian (RU), and overall average (Avg). 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 | Cross-lingual Aspect-Based Sentiment Analysis | | Dataset (including any stated split) | Multilingual ABSA (M-ABSA) (test) | | Metric | FR Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [FR Score](): Higher is better; unit: PERCENT. - [ES Score](): Higher is better; unit: PERCENT. - [NL Score](): Higher is better; unit: PERCENT. - [RU Score](): Higher is better; unit: PERCENT. - [Average Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | FR Score | Result date | Report paper | | --- | --- | --- | --- | | MTL-MSMO-DISTLL | 63.23 | Not recorded | 68fa770f1e209131cea70d8f | | Qwen2.5-7B | 63.01 | Not recorded | 68fa770f1e209131cea70d8f | | Mistral-7B-v0.3 | 59.46 | Not recorded | 68fa770f1e209131cea70d8f | | MTL-MSMO-DISTLL | 54.56 | Not recorded | 68fa770f1e209131cea70d8f | | Llama-3.1-8B | 52.65 | Not recorded | 68fa770f1e209131cea70d8f | | Gemma-2-9b-It | 50.94 | Not recorded | 68fa770f1e209131cea70d8f | | Qwen2.5-7B-Instruct | 48.88 | Not recorded | 68fa770f1e209131cea70d8f | | GPT-4o | 48.43 | Not recorded | 68fa770f1e209131cea70d8f | | Gemma-2-9B | 48.17 | Not recorded | 68fa770f1e209131cea70d8f | | Mistral-7B-Instruct-v0.3 | 37.21 | Not recorded | 68fa770f1e209131cea70d8f | | Llama-3.1-8B-Instruct | 23.15 | Not recorded | 68fa770f1e209131cea70d8f | ### MTL-MSMO-DISTLL FR Score: 63.23. Result ID: 69dcb93c47f34ce924c40415. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"XLM-R"}. This record does not assert independent reproduction. ### Qwen2.5-7B FR Score: 63.01. Result ID: 69dcb93c47f34ce924c40413. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LoRA fine-tuning","Fine-tuning Method":"LoRA"}. This record does not assert independent reproduction. ### Mistral-7B-v0.3 FR Score: 59.46. Result ID: 69dcb93c47f34ce924c40412. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Protocol":"LoRA fine-tuning","Fine-tuning Method":"LoRA"}. This record does not assert independent reproduction. ### MTL-MSMO-DISTLL FR Score: 54.56. Result ID: 69dcb93c47f34ce924c40414. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"mBERT"}. This record does not assert independent reproduction. ### Llama-3.1-8B FR Score: 52.65. Result ID: 69dcb93c47f34ce924c40411. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Protocol":"LoRA fine-tuning","Fine-tuning Method":"LoRA"}. This record does not assert independent reproduction. ### Gemma-2-9b-It FR Score: 50.94. Result ID: 69dcb93c47f34ce924c4040c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Zero-shot prompting","Prompting Template":"Wu et al. (2025b)"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct FR Score: 48.88. Result ID: 69dcb93c47f34ce924c4040f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"Zero-shot prompting","Prompting Template":"Wu et al. (2025b)"}. This record does not assert independent reproduction. ### GPT-4o FR Score: 48.43. Result ID: 69dcb93c47f34ce924c4040b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Protocol":"Zero-shot prompting","Prompting Template":"Wu et al. (2025b)"}. This record does not assert independent reproduction. ### Gemma-2-9B FR Score: 48.17. Result ID: 69dcb93c47f34ce924c40410. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training Protocol":"LoRA fine-tuning","Fine-tuning Method":"LoRA"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct-v0.3 FR Score: 37.21. Result ID: 69dcb93c47f34ce924c4040e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Protocol":"Zero-shot prompting","Prompting Template":"Wu et al. (2025b)"}. This record does not assert independent reproduction. ### Llama-3.1-8B-Instruct FR Score: 23.15. Result ID: 69dcb93c47f34ce924c4040d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training Protocol":"Zero-shot prompting","Prompting Template":"Wu et al. (2025b)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.