Solving Situation Puzzles with Large Language Model and External Reformulation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910890165534720 |
|---|---|
| author | Li, Kun Chen, Xinwei Song, Tianyou Zhou, Chengrui Liu, Zhuoran Zhang, Zhenyan Guo, Jiangjian Shan, Qing |
| author_facet | Li, Kun Chen, Xinwei Song, Tianyou Zhou, Chengrui Liu, Zhuoran Zhang, Zhenyan Guo, Jiangjian Shan, Qing |
| contents | In recent years, large language models (LLMs) have shown an impressive ability to perform arithmetic and symbolic reasoning tasks. However, we found that LLMs (e.g., ChatGPT) cannot perform well on reasoning that requires multiple rounds of dialogue, especially when solving situation puzzles. Specifically, LLMs intend to ask very detailed questions focusing on a specific aspect or same/similar questions after several rounds of Q&As. To help LLMs get out of the above dilemma, we propose a novel external reformulation methodology, where the situation puzzle will be reformulated after several rounds of Q&A or when the LLMs raise an incorrect guess. Experiments show superior performance (e.g., win rate, number of question/guess attempts) of our method than directly using LLMs for solving situation puzzles, highlighting the potential of strategic problem reformulation to enhance the reasoning capabilities of LLMs in complex interactive scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Solving Situation Puzzles with Large Language Model and External Reformulation Li, Kun Chen, Xinwei Song, Tianyou Zhou, Chengrui Liu, Zhuoran Zhang, Zhenyan Guo, Jiangjian Shan, Qing Machine Learning Computation and Language In recent years, large language models (LLMs) have shown an impressive ability to perform arithmetic and symbolic reasoning tasks. However, we found that LLMs (e.g., ChatGPT) cannot perform well on reasoning that requires multiple rounds of dialogue, especially when solving situation puzzles. Specifically, LLMs intend to ask very detailed questions focusing on a specific aspect or same/similar questions after several rounds of Q&As. To help LLMs get out of the above dilemma, we propose a novel external reformulation methodology, where the situation puzzle will be reformulated after several rounds of Q&A or when the LLMs raise an incorrect guess. Experiments show superior performance (e.g., win rate, number of question/guess attempts) of our method than directly using LLMs for solving situation puzzles, highlighting the potential of strategic problem reformulation to enhance the reasoning capabilities of LLMs in complex interactive scenarios. |
| title | Solving Situation Puzzles with Large Language Model and External Reformulation |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2503.18394 |