Solution Simulation on Student 100 1.0 (test)
0.3034ROUGE-LGPT-3.5
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-3.5Behavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=Refine2025.05 | 0.3034 | 5.71 | |
| GPT-3.5Behavior Prediction Strategy=Similarity, Solution Simulation Strategy=Refine2025.05 | 0.3005 | 5.73 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=Refine2025.05 | 0.2995 | 5.81 | |
| GPT-3.5Behavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=Refine2025.05 | 0.2986 | 5.95 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=Refine2025.05 | 0.2917 | 4.94 | |
| GPT-3.5Behavior Prediction Strategy=Random, Solution Simulation Strategy=Refine2025.05 | 0.2915 | 5.06 | |
| GPT-3.5Behavior Prediction Strategy=Level, Solution Simulation Strategy=Refine2025.05 | 0.2895 | 4.99 | |
| GPT-3.5Behavior Prediction Strategy=Level+Random, Solution Simulation Strategy=Refine2025.05 | 0.2894 | 5.13 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=Refine2025.05 | 0.2887 | 5.94 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Random, Solution Simulation Strategy=Refine2025.05 | 0.2859 | 4.98 | |
| GPT-3.5Behavior Prediction Strategy=Similarity, Solution Simulation Strategy=IO2025.05 | 0.2821 | 5.13 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=Refine2025.05 | 0.2768 | 4.55 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=IO2025.05 | 0.2761 | 4.81 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=CoT2025.05 | 0.2752 | 3.18 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=IO2025.05 | 0.2745 | 4.58 | |
| GPT-3.5Behavior Prediction Strategy=Random, Solution Simulation Strategy=IO2025.05 | 0.2745 | 3.89 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=CoT2025.05 | 0.2734 | 3.61 | |
| GPT-3.5Behavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=IO2025.05 | 0.2714 | 4.8 | |
| GPT-3.5Behavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=IO2025.05 | 0.2707 | 4.66 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=IO2025.05 | 0.2698 | 4.38 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=CoT2025.05 | 0.2691 | 3.31 | |
| GPT-4oBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=Refine2025.05 | 0.266 | 4.66 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=IO2025.05 | 0.2659 | 3.66 | |
| GPT-3.5Behavior Prediction Strategy=Level+Random, Solution Simulation Strategy=IO2025.05 | 0.2647 | 4.04 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Random, Solution Simulation Strategy=IO2025.05 | 0.2616 | 3.29 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Random, Solution Simulation Strategy=CoT2025.05 | 0.2584 | 2.36 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level, Solution Simulation Strategy=Refine2025.05 | 0.2576 | 3.31 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=CoT2025.05 | 0.2557 | 2.83 | |
| GPT-4oBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=Refine2025.05 | 0.2515 | 3.47 | |
| GPT-4oBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=IO2025.05 | 0.249 | 3.35 | |
| GPT-3.5Behavior Prediction Strategy=Level, Solution Simulation Strategy=IO2025.05 | 0.2439 | 2.91 | |
| GPT-3.5Behavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=CoT2025.05 | 0.2428 | 2.81 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=Refine2025.05 | 0.2409 | 3.06 | |
| GPT-4oBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=IO2025.05 | 0.2397 | 3.36 | |
| GPT-3.5Behavior Prediction Strategy=Similarity, Solution Simulation Strategy=CoT2025.05 | 0.2349 | 2.38 | |
| GPT-3.5Behavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=CoT2025.05 | 0.2344 | 2.56 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level, Solution Simulation Strategy=IO2025.05 | 0.2338 | 2.35 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=Refine2025.05 | 0.2337 | 2.99 | |
| GPT-4oBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=Refine2025.05 | 0.2318 | 2.85 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=Refine2025.05 | 0.2315 | 2.93 | |
| GPT-4oBehavior Prediction Strategy=Random, Solution Simulation Strategy=IO2025.05 | 0.2299 | 2.32 | |
| Claude-3.5-SonnetBehavior Prediction Strategy=Level, Solution Simulation Strategy=CoT2025.05 | 0.2293 | 1.97 | |
| GPT-4oBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=CoT2025.05 | 0.2276 | 2.24 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=Refine2025.05 | 0.2275 | 2.33 | |
| GPT-3.5Behavior Prediction Strategy=Random, Solution Simulation Strategy=CoT2025.05 | 0.2268 | 2.15 | |
| GPT-4oBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=CoT2025.05 | 0.2265 | 2.33 | |
| GPT-3.5Behavior Prediction Strategy=Level+Random, Solution Simulation Strategy=CoT2025.05 | 0.2263 | 2.43 | |
| GPT-4oBehavior Prediction Strategy=Random, Solution Simulation Strategy=Refine2025.05 | 0.2251 | 2.54 | |
| GPT-4oBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=IO2025.05 | 0.2251 | 2.74 | |
| GPT-4oBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=Refine2025.05 | 0.222 | 2.17 | |
| GPT-3.5Behavior Prediction Strategy=Level, Solution Simulation Strategy=CoT2025.05 | 0.2213 | 2.12 | |
| GPT-4oBehavior Prediction Strategy=Level, Solution Simulation Strategy=Refine2025.05 | 0.2182 | 1.83 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Random, Solution Simulation Strategy=Refine2025.05 | 0.2152 | 2.08 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level, Solution Simulation Strategy=Refine2025.05 | 0.2145 | 1.45 | |
| GPT-4oBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=IO2025.05 | 0.2114 | 1.97 | |
| GPT-4oBehavior Prediction Strategy=Random, Solution Simulation Strategy=CoT2025.05 | 0.2096 | 1.84 | |
| GPT-4oBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=CoT2025.05 | 0.2077 | 2.12 | |
| GPT-4oBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=CoT2025.05 | 0.1944 | 1.4 | |
| GPT-4oBehavior Prediction Strategy=Level, Solution Simulation Strategy=IO2025.05 | 0.1892 | 1.26 | |
| GPT-4oBehavior Prediction Strategy=Level, Solution Simulation Strategy=CoT2025.05 | 0.1867 | 1.14 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=IO2025.05 | 0.1749 | 0.98 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=IO2025.05 | 0.1617 | 0.92 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Prototype Mapping, Solution Simulation Strategy=CoT2025.05 | 0.1533 | 0.93 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=IO2025.05 | 0.152 | 0.82 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level, Solution Simulation Strategy=IO2025.05 | 0.1456 | 0.65 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level+Similarity, Solution Simulation Strategy=CoT2025.05 | 0.1448 | 0.87 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=CoT2025.05 | 0.1394 | 0.64 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Similarity, Solution Simulation Strategy=CoT2025.05 | 0.1392 | 0.81 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level+Random, Solution Simulation Strategy=IO2025.05 | 0.1383 | 0.66 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Level, Solution Simulation Strategy=CoT2025.05 | 0.1377 | 0.58 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Random, Solution Simulation Strategy=CoT2025.05 | 0.1357 | 0.62 | |
| LLaMA-3.3-70B-InstructBehavior Prediction Strategy=Random, Solution Simulation Strategy=IO2025.05 | 0.1336 | 0.6 |