Eating Disorder Detection on JiraiBench 1.0 (test)
79.99Macro F1SAS (English version)
Evaluation Results
| Method | Links | |
|---|---|---|
| SAS (English version)LLM Backbone=DeepSeek V3.22026.01 | 79.99 | |
| Self-RefineLLM Backbone=DeepSeek V3.22026.01 | 76.94 | |
| OWLLLM Backbone=DeepSeek V3.22026.01 | 76.86 | |
| S^3 AgentLLM Backbone=DeepSeek V3.22026.01 | 75.85 | |
| Zero-shotLLM Backbone=DeepSeek V3.22026.01 | 74.15 | |
| Zero-shot CoTLLM Backbone=DeepSeek V3.22026.01 | 73.86 | |
| SAS (English version)LLM Backbone=Gemma-3-12B-it2026.01 | 73.8 | |
| Plan-and-SolveLLM Backbone=DeepSeek V3.22026.01 | 72.74 | |
| SAS (English version)LLM Backbone=Ministral-3-8B2026.01 | 69.99 | |
| S^3 AgentLLM Backbone=Gemma-3-12B-it2026.01 | 69.06 | |
| Self-RefineLLM Backbone=Gemma-3-12B-it2026.01 | 68.66 | |
| Self-RefineLLM Backbone=Qwen-2.5-7B2026.01 | 61.36 | |
| Zero-shotLLM Backbone=Ministral-3-8B2026.01 | 57.58 | |
| Zero-shot CoTLLM Backbone=Ministral-3-8B2026.01 | 57.53 | |
| SAS (English version)LLM Backbone=Llama-3.1-8B2026.01 | 56.42 | |
| S^3 AgentLLM Backbone=Qwen-2.5-7B2026.01 | 55.24 | |
| Plan-and-SolveLLM Backbone=Ministral-3-8B2026.01 | 53.96 | |
| Plan-and-SolveLLM Backbone=Qwen-2.5-7B2026.01 | 53.17 | |
| S^3 AgentLLM Backbone=Ministral-3-8B2026.01 | 52.99 | |
| Zero-shotLLM Backbone=Llama-3.1-8B2026.01 | 52.95 | |
| OWLLLM Backbone=Qwen-2.5-7B2026.01 | 52.9 | |
| Self-RefineLLM Backbone=Ministral-3-8B2026.01 | 52.8 | |
| SAS (English version)LLM Backbone=Qwen-2.5-7B2026.01 | 52.8 | |
| Zero-shot CoTLLM Backbone=Llama-3.1-8B2026.01 | 52.56 | |
| Zero-shot CoTLLM Backbone=Qwen-2.5-7B2026.01 | 52.42 | |
| OWLLLM Backbone=Ministral-3-8B2026.01 | 50.18 | |
| Self-RefineLLM Backbone=Llama-3.1-8B2026.01 | 49.76 | |
| Zero-shot CoTLLM Backbone=Gemma-3-12B-it2026.01 | 47.46 | |
| Zero-shotLLM Backbone=Gemma-3-12B-it2026.01 | 46.29 | |
| Plan-and-SolveLLM Backbone=Gemma-3-12B-it2026.01 | 45.56 | |
| Plan-and-SolveLLM Backbone=Llama-3.1-8B2026.01 | 45.23 | |
| Zero-shotLLM Backbone=Qwen-2.5-7B2026.01 | 44.52 | |
| OWLLLM Backbone=Gemma-3-12B-it2026.01 | 40.72 | |
| S^3 AgentLLM Backbone=Llama-3.1-8B2026.01 | 39.56 | |
| OWLLLM Backbone=Llama-3.1-8B2026.01 | 38.79 |