DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
Uloženo v:
| Vydáno v: | arXiv.org (Dec 23, 2024), p. n/a |
|---|---|
| Hlavní autor: | |
| Další autoři: | , , , |
| Vydáno: |
Cornell University Library, arXiv.org
|
| Témata: | |
| On-line přístup: | Citation/Abstract Full text outside of ProQuest |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3126995661 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 3126995661 | ||
| 045 | 0 | |b d20241223 | |
| 100 | 1 | |a Tong, Yuxuan | |
| 245 | 1 | |a DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving | |
| 260 | |b Cornell University Library, arXiv.org |c Dec 23, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Solving mathematical problems requires advanced reasoning abilities and presents notable challenges for large language models. Previous works usually synthesize data from proprietary models to augment existing datasets, followed by instruction tuning to achieve top-tier results. However, our analysis of these datasets reveals severe biases towards easy queries, with frequent failures to generate any correct response for the most challenging queries. Hypothesizing that difficult queries are crucial to learn complex reasoning, we propose Difficulty-Aware Rejection Tuning (DART), a method that allocates difficult queries more trials during the synthesis phase, enabling more extensive training on difficult samples. Utilizing DART, we have created new datasets for mathematical problem-solving that focus more on difficult queries and are substantially smaller than previous ones. Remarkably, our synthesis process solely relies on a 7B-sized open-weight model, without reliance on the commonly used proprietary GPT-4. We fine-tune various base models on our datasets ranging from 7B to 70B in size, resulting in a series of strong models called DART-MATH. In comprehensive in-domain and out-of-domain evaluation on 6 mathematical benchmarks, DART-MATH outperforms vanilla rejection tuning significantly, being superior or comparable to previous arts, despite using much smaller datasets and no proprietary models. Furthermore, our results position our synthetic datasets as the most effective and cost-efficient publicly available resources for advancing mathematical problem-solving. | |
| 653 | |a Problem solving | ||
| 653 | |a Datasets | ||
| 653 | |a Tuning | ||
| 653 | |a Rejection | ||
| 653 | |a Large language models | ||
| 653 | |a Mathematical problems | ||
| 653 | |a Proprietary | ||
| 653 | |a Query processing | ||
| 653 | |a Synthetic data | ||
| 653 | |a Reasoning | ||
| 700 | 1 | |a Zhang, Xiwen | |
| 700 | 1 | |a Wang, Rui | |
| 700 | 1 | |a Wu, Ruidong | |
| 700 | 1 | |a He, Junxian | |
| 773 | 0 | |t arXiv.org |g (Dec 23, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3126995661/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2407.13690 |