Give me a hint: Can LLMs take a hint to solve math problems?
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929585441996800 |
|---|---|
| author | Agrawal, Vansh Singla, Pratham Miglani, Amitoj Singh Garg, Shivank Mangal, Ayush |
| author_facet | Agrawal, Vansh Singla, Pratham Miglani, Amitoj Singh Garg, Shivank Mangal, Ayush |
| contents | While state-of-the-art LLMs have shown poor logical and basic mathematical reasoning, recent works try to improve their problem-solving abilities using prompting techniques. We propose giving "hints" to improve the language model's performance on advanced mathematical problems, taking inspiration from how humans approach math pedagogically. We also test robustness to adversarial hints and demonstrate their sensitivity to them. We demonstrate the effectiveness of our approach by evaluating various diverse LLMs, presenting them with a broad set of problems of different difficulties and topics from the MATH dataset and comparing against techniques such as one-shot, few-shot, and chain of thought prompting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05915 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Give me a hint: Can LLMs take a hint to solve math problems? Agrawal, Vansh Singla, Pratham Miglani, Amitoj Singh Garg, Shivank Mangal, Ayush Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition While state-of-the-art LLMs have shown poor logical and basic mathematical reasoning, recent works try to improve their problem-solving abilities using prompting techniques. We propose giving "hints" to improve the language model's performance on advanced mathematical problems, taking inspiration from how humans approach math pedagogically. We also test robustness to adversarial hints and demonstrate their sensitivity to them. We demonstrate the effectiveness of our approach by evaluating various diverse LLMs, presenting them with a broad set of problems of different difficulties and topics from the MATH dataset and comparing against techniques such as one-shot, few-shot, and chain of thought prompting. |
| title | Give me a hint: Can LLMs take a hint to solve math problems? |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.05915 |