基于思维链微调的交通事故判责语言模型研究

doi:10.16265/j.cnki.issn1003-3033.2026.S1.0031

中国安全科学学报 ›› 2026, Vol. 36 ›› Issue (S1): 210-216.doi: 10.16265/j.cnki.issn1003-3033.2026.S1.0031

• 智能安全技术 • 上一篇

基于思维链微调的交通事故判责语言模型研究

胥川¹^,²^,³(), 李博¹^,²^,³, 胡家琳¹^,²^,³, 罗丹¹^,²^,³, 江欣国¹^,²^,³

¹ 西南交通大学交通运输与物流学院, 四川成都 611756
² 综合交通运输智能化国家地方联合工程实验室, 四川成都 610031
³ 综合交通大数据应用技术国家工程实验室, 四川成都 610031

收稿日期:2026-02-21 修回日期:2026-04-20 出版日期:2026-06-30
作者简介:
胥川 (1987—),男,四川南充人,博士,副教授,主要从事交通安全应用方面的研究。E-mail:xuchuan@swjtu.edu.cn。
江欣国教授
基金资助:
四川省自然学科基金面上项目资助(2024NSFSC0182); 智能警务四川省重点实验室开放课题项目(ZNJW2024KFZD001)

Language models for traffic accident liability determination based on chain-of-thought fine-tuning

Xu Chuan¹^,²^,³(), Li Bo¹^,²^,³, Hu Jialin¹^,²^,³, Luo Dan¹^,²^,³, Jiang Xinguo¹^,²^,³

¹ School of Transportation and Logistics, Southwest Jiaotong University, Chengdu Sichuan 611756, China
² National United Engineering Laboratory of Integrated and Intelligent Transportation, Chengdu Sichuan 610031, China
³ National Engineering Laboratory for Integrated Transportation Big Data Application Technology, Chengdu Sichuan 610031, China

Received:2026-02-21 Revised:2026-04-20 Published:2026-06-30

摘要/Abstract

摘要：

为解决道路交通事故判责中人工效率低、传统机器学习模型复杂事故情景下推理、泛化和可解释性不足的问题,构建基于大语言模型的思维链微调框架,以2014—2025年间870篇加州自动驾驶车辆事故报告和加州交通法规为基础,构建微调数据,设计专家模板引导的判责推理路径,结合知识蒸馏方法实施两阶段微调训练,将法规知识、专业推理过程及结构化输出模式内化到小规模语言模型。结果表明:零样本条件下,与未微调模型相比,责任方匹配准确率由30.19%提升至97.18%,推理质量综合得分由1.33提升至4.64;微调后小规模模型(3B)在零样本条件下,完全正确率、参与方正确率及责任方匹配准确率均优于开源大模型(235B),核心推理能力评分高出7.4%。

关键词: 思维链微调, 交通事故判责, 大语言模型, 可解释性, 知识蒸馏

Abstract:

In response to low manual efficiency and the insufficient reasoning, generalization, and interpretability of traditional machine learning models under complex accident scenarios in road traffic accident liability determination, a chain-of-thought (CoT) fine-tuning framework based on large language model (LLM) was constructed. Fine-tuning data were built from 870 California autonomous vehicle accident reports (2014-2025) and the California traffic laws. An expert-template-guided reasoning path for liability determination was designed. A two-stage fine-tuning practice was implemented using knowledge distillation. Legal knowledge, professional reasoning processes, and structured output patterns were internalized into a small-scale language model. The results show that compared with the non-fine-tuned model, the responsible party matching accuracy is improved from 30.19% to 97.18%, with the comprehensive reasoning quality score raised from 1.33 to 4.64 under zero-shot conditions. In zero-shot settings, the fine-tuned small-scale model (3B) outperforms a 235B open-source large model in full correctness, party correctness, and responsible party matching accuracy, with a 7.4% higher core reasoning ability score.

Key words: chain-of-thought fine-tuning, traffic accident liability determination, large language model, interpretability, knowledge distillation

中图分类号:

X913.2安全信息论

胥川, 李博, 胡家琳, 罗丹, 江欣国. 基于思维链微调的交通事故判责语言模型研究[J]. 中国安全科学学报, 2026, 36(S1): 210-216.

Xu Chuan, Li Bo, Hu Jialin, Luo Dan, Jiang Xinguo. Language models for traffic accident liability determination based on chain-of-thought fine-tuning[J]. China Safety Science Journal, 2026, 36(S1): 210-216.

图/表 9

图1

图2

图3

图4

表1

表2

表3

表4

图5

参考文献 16

[1]	世界卫生组织. 2023年全球道路安全状况报告[R], 2023.
	World Health Organization. Global status report on road safety 2023[R], 2023.
[2]	国家统计局. 中国统计年鉴2024[M]. 北京: 中国统计出版社, 2024: 755.
[3]	余凌云. 道路交通事故责任认定研究[J]. 法学研究, 2016, 38(6): 126-139.
	Yu Lingyun. Determination of liabilities for road traffic accident[J]. Chinese Journal of Law, 2016, 38(6): 126-139.
[4]	马社强. 道路交通事故当事人责任认定有关问题研究[J]. 中国人民公安大学学报(自然科学版), 2018, 24(2): 84-87.
[5]	黄钢, 高岩, 赵冬, 等. 交通事故智能定责深度学习集成方法研究[J]. 交通运输系统工程与信息, 2025(3): 299-307.
	Huang Gang, Gao Yan, Zhao Dong, et al. Deep learning ensemble method for intelligent liability determination in traffic accidents[J]. Journal of Transportation Systems Engineering and Information Technology, 2025(3): 299-307.
[6]	Brown T, Mann B, Ryder N, et al. Language models are few-shot learners[J]. Advances in Neural Information Processing Systems, 2020, 33: 1 877-1 901.
[7]	Touvron H, Lavril T, Izacard G, et al. Llama:open and efficient foundation language models[PP/OL]. arXiv(2023-02-27)[2026-03-11]. https://doi.org/10.48550/arXiv.2302.13971.
[8]	Yang An, Li Anfeng, Yang Baosong, et al. Qwen3 technical report[PP/OL]. arXiv(2025-05-14)[2026-03-09]. https://doi.org/10.48550/arXiv.2505.09388.
[9]	Yao Shunyu, Ke Qingqing, Wang Qiwei, et al. Lawyer GPT: a legal large language model with enhanced domain knowledge and reasoning capabilities[C]. Proceedings of the 2024 3rd International Symposium on Robotics, Artificial Intelligence and Information Engineering, 2024: 108-112.
[10]	Shi Juanming, Guo Qinglang, Liao Yong, et al. Legal GPT: legal chain of thought for the legal large language model multi-agent framework[C]. International Conference on Intelligent Computing, 2024: 25-37.
[11]	Wei J, Wang Xuezhi, Schuurmans D, et al. Chain-of-thought prompting elicits reasoning in large language models[J]. Advances in Neural Information Processing Systems, 2022, 35: 24 824-24 837.
[12]	Suzgun M, Scales N, Schärli N, et al. Challenging BIG-bench tasks and whether chain-of-thought can solve them[C]. Findings of the Association for Computational Linguistics: ACL 2023, 2023: 13 003-13 051.
[13]	Tan Zhen, Li Dawei, Wang Song, et al. Large language models for data annotation and synthesis: a survey[C]. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024: 930-957.
[14]	Zhen Hao, Shi Yucheng, Huang Yongcan, et al. Leveraging large language models with chain-of-thought and prompt engineering for traffic crash severity analysis and inference[J]. Computers, 2024, 13(9): DOI: 10.3390/computers13090232.
[15]	Li S, Chen J, Shen Y, et al. Explanations from large language models make small reasoners better[PP/OL]. arXiv(2022-10-13)[2026-02-22]. https://doi.org/10.48550/arXiv.2210.06726.
[16]	Hu E J, Shen Yelong, Wallis P, et al. LoRA:low-rank adaptation of large language models[PP/OL]. V2. arXiv(2021-06-17)[2026-02-12]. https://doi.org/10.48550/arXiv.2106.09685.

提示策略	M₁	M₂	M₃
FS	FS-M₁	FS-M₂	FS-M₃
ZS	ZS-M₁	ZS-M₂	ZS-M₃
CoT	CoT-M₁	CoT-M₂	CoT-M₃

系统提示		你是一个交通事故分析的专家,分析事故描述中的判责划分,给出正确的加州法规引用和多方责任划分,并结构化输出结果
用户输入	ZS提示	{事故描述}
	CoT提示	{事故描述} + {定制化CoT提示}
	FS提示	{事故描述} + {1个完整的输入输出案例}

模型	组别	完全正确率/%	参与方正确率/%	责任方匹配准确率/%
M₁	FS-M₁	21.33	48	66.67
	ZS-M₁	18.67	70.67	30.19
	CoT-M₁	45.33	82.67	56.45
M₂	FS-M₂	81.33	86.67	100
	ZS-M₂	89.33	94.67	97.18
	CoT-M₂	88	93.33	95.71
M₃	FS-M₃	78.67	89.33	89.55
	ZS-M₃	70.67	85.33	82.81
	CoT-M₃	88	97.33	90.41

模型	组别	D₁	D₂	D₃	D₄	D₁—D₃均值
M₁	FS-M₁	2.6	3.16	2.57	4.85	2.78
	ZS-M₁	1.91	1.03	1.04	0.23	1.33
	CoT-M₁	2.88	1.63	2.2	2.56	2.24
M₂	FS-M₂	4.44	4.59	3.96	5	4.33
	ZS-M₂	4.73	4.83	4.35	5	4.64
	CoT-M₂	4.65	4.76	4.27	4.99	4.56
M₃	FS-M₃	4.68	4.79	4.44	5	4.64
	ZS-M₃	4.23	4.37	4.36	2.41	4.32
	CoT-M₃	4.7	4.84	4.55	4.24	4.70

基于思维链微调的交通事故判责语言模型研究

Language models for traffic accident liability determination based on chain-of-thought fine-tuning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 16

相关文章 8

编辑推荐

Metrics

本文评价

[1]	刘行, 张巍, 李安康, 吉虎, 孙昌健, 叶霄. 垂域大语言模型下盐穴储氢库风险分析与处置方法[J]. 中国安全科学学报, 2026, 36(8): 187-196.
[2]	杨跃翔, 刘学文, 涂新雨, 郑怀城, 许应成. 基于LLMs与KG的智能消费产品质量安全风险分析[J]. 中国安全科学学报, 2026, 36(4): 271-280.
[3]	李华, 吴立舟, 李新宏, 张越, 冯垚, 覃紫芸. 基于DeepSeek与RAG的事故调查报告知识生成模型[J]. 中国安全科学学报, 2026, 36(1): 26-34.
[4]	秦跃平, 唐飞, 王海蓉, 王鹏, 郭铭彦, 王世斌. 基于KOA-BiLSTM的矿井淋水井筒风温预测模型及可解释性分析[J]. 中国安全科学学报, 2025, 35(7): 40-47.
[5]	刘亚栋, 刘贤, 胡贺松, 陈航, 乔升访. 基于可解释机器学习模型的基坑围护墙变形影响因素分析[J]. 中国安全科学学报, 2025, 35(4): 110-119.
[6]	杨艺, 王东麟, 陈振颂. 基于大语言模型智能体的汽车安全风险判别:以投诉文本为驱动[J]. 中国安全科学学报, 2025, 35(12): 204-212.
[7]	赵荣泳, 彭星竹, 韦炳宇, 曾国毅, 刘丰年, 闫鹏. 大语言模型与知识图谱在建筑安全领域的技术发展综述[J]. 中国安全科学学报, 2025, 35(12): 1-7.
[8]	唐海洋, 刘振翼, 陈东平, 初庆钊. ChatSOS:基于大语言模型的安全工程知识问答系统[J]. 中国安全科学学报, 2024, 34(8): 178-185.