全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于思维链的通用语言模型推理能力研究
Research on the Reasoning Ability of General Language Model Based on Chain of Thought

DOI: 10.12677/airr.2025.142026, PP. 259-267

Keywords: 上下文学习,思维链,逻辑推理,ChatGLM2
In-Context Learning
, Chain of Thought, Logical Reasoning, ChatGLM2

Full-Text   Cite this paper   Add to My Lib

Abstract:

为改善参数量较小的大模型在逻辑推理任务中的性能不足,以及微调模型复杂度高、资源受限的问题,本文采用上下文学习(ICL)方法,通过引入思维链提示(CoT)构建示例,探索在无需微调模型参数的情况下提升通用语言模型ChatGLM2-6B推理性能的可行性。以Zero-Shot-CoT生成的思维链为基准,结合随机检索与多种聚类方法优化示例选择策略。实验结果表明,不同示例选择策略可使模型推理能力平均提升10%,验证了思维链提示对推理性能的增强效果,并显示优化示例策略能够在资源受限条件下实现大模型的高效利用。本研究为提升语言模型逻辑推理能力和下游任务性能提供了新思路,并为低资源场景下的大模型应用奠定了理论基础。
To improve the underperformance of large models with small parameter counts in logical reasoning tasks, as well as the high complexity and resource constraints of fine-tuning the models. This paper adopts In-Context-Learning approach to explore the feasibility of improving the reasoning performance of the General Language Model, ChatGLM2-6B, without the need of fine-tuning the parameters of the model, by introducing Chain-of-Thought (CoT) prompt to construct examples. The CoT generated by Zero-Shot-CoT are used as the benchmark, and the example selection strategy is optimized by combining random retrieval with multiple clustering methods. The experimental results show that different example selection strategies can improve the model’s reasoning ability by 10% on average, verifying the enhancing effect of CoT prompts on reasoning performance, and showing that the optimized example strategy can achieve the efficient utilization of large models under resource-constrained conditions. This study provides new ideas for improving the logical reasoning ability of language models and the performance of downstream tasks, and lays a theoretical foundation for the application of large models in low-resource scenarios.

References

[1]  Dong, Q., Li, L., Dai, D., et al. (2022) A Survey on In-Context Learning. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 1107-1128.
[2]  Wei, J., Wang, X.Z., Schuurmans, D., Bosma, M., Chi, E., Le, Q. and Zhou, D. (2022) Chain of Thought Prompting Elicits Reasoning in Large Language Models. Advances in Neural Information Processing Systems, 35, 24824-24837.
[3]  Liu, J.C., Shen, D.H., Zhang, Y.Z., Dolan, B., Carin, L. and Chen, W.Z. (2022) What Makes Good In-Context Examples for GPT3? Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Dublin, 27 May 2022, 100-114.
[4]  Rubin, O., Herzig, J. and Berant, J. (2022) Learning to Retrieve Prompts for In-Context Learning. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, July 2022, 2655-2671.
https://doi.org/10.18653/v1/2022.naacl-main.191
[5]  Wang, Y., Kordi, Y., Mishra, S., Liu, A., Smith, N.A., Khashabi, D., et al. (2023) Self-Instruct: Aligning Language Models with Self-Generated Instructions. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Volume 1, 13484-13508.
https://doi.org/10.18653/v1/2023.acl-long.754
[6]  王东清, 芦飞, 张炳会, 李道童, 彭继阳, 王兵, 姚藩益, 艾山彬. 大语言模型中提示词工程综述[J]. 计算机系统应用, 2025, 34(1): 1-10.
http://www.c-s-a.org.cn/1003-3254/9782.html
[7]  Kojima, T., Gu, S.S., Reid, M., Matsuo, Y. and Iwasawa, Y. (2022) Large Language Models Are Zero-Shot Reasoners. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, 28 November-9 December 2022, 22199-22213.
[8]  Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., et al. (2020) Language Models Are Few-Shot Learners. Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6-12 December 2020, 1877-1901.
[9]  Zhou, D., Schärli, N., Hou, L., Wei, J., Scales, N., Wang, X.Z., et al. (2022) Least-to-Most Prompting Enables Complex Reasoning in Large Language Models. The Eleventh International Conference on Learning Representations.
[10]  Du, Z., Qian, Y., Liu, X., Ding, M., Qiu, J., Yang, Z., et al. (2022) GLM: General Language Model Pretraining with Autoregressive Blank Infilling. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Volume 1, 320-335.
https://doi.org/10.18653/v1/2022.acl-long.26
[11]  Zhang, Z.S., Zhang, A., Li, M. and Smola, A. (2022) Automatic Chain of Thought Prompting in Large Language Models. The Eleventh International Conference on Learning Representations.
[12]  Ho, N., Schmid, L. and Yun, S.-Y. (2022) Large Language Models Are Reasoning Teachers. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, Volume 1, Long Papers, 14852-14882.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133