{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:34:10Z","timestamp":1772120050327,"version":"3.50.1"},"reference-count":45,"publisher":"Wiley","issue":"27-28","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2025,12,25]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>This paper presents a soft and novel context\u2010aware prompt engineering framework to enable adaptive and safe integration of large language models (LLMs) into autonomous vehicle (AV) systems. Unlike prior works, which employed static prompts or offline decision logic, our method dynamically creates prompts based on multimodal context, including speech commands, environmental cues (e.g., traffic, weather), and urgency levels. A hierarchical prioritization model is introduced to classify instructions according to safety sensitivity, enabling fine\u2010grained control and real\u2010time response in high\u2010risk AV scenarios. The system integrates speech\u2010to\u2010text (STT) transcription, text inputs, environmental context, and LLMs. Assessment of the Talk2Car dataset and a complementary noisy\u2010speech testbed indicated consistent improvements in accuracy, precision, recall, and F1 across four backbone LLMs (BERT, GPT\u20102, SALMON, and SALMONN). These results demonstrate the effectiveness of prompt\u2010level adaptation in ensuring robustness and scalability in real\u2010world AV deployments.<\/jats:p>","DOI":"10.1002\/cpe.70392","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T18:44:18Z","timestamp":1761763458000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Context\u2010Aware Prompt Engineering for Large Language Models in Autonomous Vehicles"],"prefix":"10.1002","volume":"37","author":[{"given":"Shirin","family":"Abbasi","sequence":"first","affiliation":[{"name":"Department of Computer Engineering University of Science and Culture  Tehran Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir Masoud","family":"Rahmani","sequence":"additional","affiliation":[{"name":"Future Technology Research Center National Yunlin University of Science and Technology  Douliou Yunlin Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"e_1_2_15_2_1","first-page":"334","volume-title":"International Conference on Computational Linguistics and Intelligent Text Processing","author":"Okur S. H.","year":"2019"},{"key":"e_1_2_15_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/info14100555"},{"key":"e_1_2_15_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/su15075749"},{"key":"e_1_2_15_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23094537"},{"key":"e_1_2_15_6_1","unstructured":"W.Tang G.Yu X.Sun et al. \u201cSALMONN: Towards Generic Hearing Abilities for Large Language Models \u201d2023 arXiv preprint arXiv:2310.13289."},{"key":"e_1_2_15_7_1","doi-asserted-by":"crossref","unstructured":"K.\u2010W.Chang W.\u2010C.Tseng S.\u2010W.Li andH.\u2010Y.Lee \u201cSpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks \u201d2022 arXiv preprint arXiv:2203.16773.","DOI":"10.21437\/Interspeech.2022-10610"},{"key":"e_1_2_15_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3119921"},{"key":"e_1_2_15_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"e_1_2_15_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-023-06172-w"},{"key":"e_1_2_15_11_1","unstructured":"Y.Fathullah C.Wu E.Lakomkin et al. \u201cPrompting Large Language Models With Speech Recognition Abilities \u201d2023 arXiv Preprint arXiv:2307.11795."},{"key":"e_1_2_15_12_1","unstructured":"S.Wang Z.Yu X.Jiang et al. \u201cOmniDrive: A Holistic LLM\u2010Agent Framework for Autonomous Driving With 3D Perception Reasoning and Planning \u201d2024 arXiv preprint arXiv:2405.01533."},{"key":"e_1_2_15_13_1","article-title":"Salmon: Self\u2010Alignment With Principle\u2010Following Reward Models","author":"Sun Z.","year":"2023","journal-title":"CoRR"},{"key":"e_1_2_15_14_1","unstructured":"H.Zhang N.Si Y.Chen et al. \u201cTuning Large Language Models for End\u2010To\u2010End Speech Translation \u201d20232023 arXiv Preprint arXiv:2310.02050."},{"key":"e_1_2_15_15_1","unstructured":"X. L.LiandP.Liang \u201cPrefix\u2010Tuning: Optimizing Continuous Prompts for Generation \u201d2021 arXiv preprint arXiv:2101.00190."},{"key":"e_1_2_15_16_1","unstructured":"T.Gao A.Fisch andD.Chen \u201cMaking Pre\u2010Trained Language Models Better Few\u2010Shot Learners \u201d2020 arXiv preprint arXiv:2012.15723."},{"key":"e_1_2_15_17_1","doi-asserted-by":"crossref","unstructured":"Y.Xu D.Lu J.Liang et al. \u201cSource Prompt: Coordinated Pre\u2010Training of Language Models on Diverse Corpora From Multiple Sources \u201d2024 inProceedings of the 33rd ACM International Conference on Information and Knowledge Management 2732\u20132741.","DOI":"10.1145\/3627673.3679835"},{"key":"e_1_2_15_18_1","doi-asserted-by":"crossref","unstructured":"B.Lester R.Al\u2010Rfou andN.Constant \u201cThe Power of Scale for Parameter\u2010Efficient Prompt Tuning \u201d2021 arXiv preprint arXiv:2104.08691.","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_2_15_19_1","doi-asserted-by":"crossref","unstructured":"Y.Duan Q.Zhang andR.Xu \u201cPrompting Multimodal Tokens to Enhance End\u2010To\u2010End Autonomous Driving Imitation Learning With LLMs\u201d2024 arXiv Preprint arXiv:2404.04869.","DOI":"10.1109\/ICRA57147.2024.10611614"},{"key":"e_1_2_15_20_1","doi-asserted-by":"crossref","unstructured":"X.Zheng L.Wu Z.Yan et al. \u201cLarge Language Models Powered Context\u2010Aware Motion Prediction \u201d2024 arXiv preprint arXiv:2403.11057.","DOI":"10.1109\/IROS58592.2024.10802397"},{"key":"e_1_2_15_21_1","doi-asserted-by":"crossref","unstructured":"Z.Guo A.Lykov Z.Yagudin M.Konenkov andD.Tsetserukou \u201cCo\u2010Driver: VLM\u2010Based Autonomous Driving Assistant With Human\u2010Like Behavior and Understanding for Complex Road Scenes \u201d2024 arXiv Preprint arXiv:2405.05885.","DOI":"10.1109\/FLLM63129.2024.10852498"},{"key":"e_1_2_15_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3484528"},{"key":"e_1_2_15_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3268703"},{"key":"e_1_2_15_24_1","doi-asserted-by":"crossref","unstructured":"R.Zhong K.Lee Z.Zhang andD.Klein \u201cAdapting Language Models for Zero\u2010Shot Learning by Meta\u2010Tuning on Dataset and Prompt Collections \u201d2021 arXiv Preprint arXiv:2104.04670.","DOI":"10.18653\/v1\/2021.findings-emnlp.244"},{"key":"e_1_2_15_25_1","doi-asserted-by":"crossref","unstructured":"T.Deruyttere S.Vandenhende D.Grujicic L.Van Gool andM.\u2010F.Moens \u201cTalk2Car: Taking Control of Your Self\u2010Driving Car \u201d2019 arXiv Preprint arXiv:1909.10838.","DOI":"10.18653\/v1\/D19-1215"},{"key":"e_1_2_15_26_1","unstructured":"Thunlp \u201cPromptPapers Repository [Online] \u201d2024 https:\/\/github.com\/thunlp\/PromptPapers."},{"key":"e_1_2_15_27_1","unstructured":"M.Azarafza M.Nayyeri C.Steinmetz S.Staab andA.Rettberg \u201cHybrid Reasoning Based on Large Language Models for Autonomous Car Driving \u201d20324 arXiv preprint arXiv:2402.13602."},{"key":"e_1_2_15_28_1","first-page":"1123","article-title":"Speech\u2010Augmented Prompt Tuning for Enhanced Speech\u2010To\u2010Text Accuracy","volume":"32","author":"Fathullah A.","year":"2024","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"e_1_2_15_29_1","unstructured":"IBM \u201cSelf\u2010Alignment with Principle\u2010Following Reward Models \u201d \u201cSALMON Code Repository [Online] \u201d2023 GitHub https:\/\/github.com\/IBM\/SALMON."},{"key":"e_1_2_15_30_1","unstructured":"J.Stojkovic E.Choukse C.Zhang I.Goiri andJ.Torrellas \u201cTowards Greener LLMs: Bringing Energy\u2010Efficiency to the Forefront of LLM Inference \u201d2024 arXiv Preprint arXiv:2403.20306."},{"key":"e_1_2_15_31_1","doi-asserted-by":"crossref","unstructured":"H.Ghaith A.Rawashdeh andS.Al Zubi \u201cTransfer Learning in Data Fusion at Autonomous Driving \u201dIn2021 International Conference on Information Technology(ICIT) IEEE 714\u2013718.","DOI":"10.1109\/ICIT52682.2021.9491721"},{"key":"e_1_2_15_32_1","unstructured":"Deep\u2010Info \u201cSALMONN Code Repository [Online] \u201d2023 GitHub https:\/\/github.com\/deep\u2010info\/SALMONN."},{"key":"e_1_2_15_33_1","unstructured":"M. V.Koroteev \u201cBERT: A Review of Applications in Natural Language Processing and Understanding \u201d2021 arXiv Preprint arXiv:2103.11943."},{"key":"e_1_2_15_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2023.08.012"},{"key":"e_1_2_15_35_1","unstructured":"Talk2Car \u201cTalk2Car Dataset [Dataset] \u201d2019 GitHub https:\/\/github.com\/talk2car\/Talk2Car."},{"key":"e_1_2_15_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_2_15_37_1","first-page":"1877","article-title":"Language Models Are Few\u2010Shot Learners","volume":"33","author":"Brown T.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_15_38_1","unstructured":"S. L.Smith P.Kindermans andQ. V.Le \u201cDon't Decay the Learning Rate. Increase the Batch Size \u201d2017 arXiv preprint arXiv:1711.05187."},{"key":"e_1_2_15_39_1","doi-asserted-by":"crossref","unstructured":"J.Devlin M.\u2010W.Chang K.Lee andK.Toutanova \u201cBert: Pre\u2010Training of Deep Bidirectional Transformers for Language Understanding \u201dinProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Volume 1(Long and Short Papers) 4171\u20134186 2019.","DOI":"10.18653\/v1\/N19-1423"},{"issue":"8","key":"e_1_2_15_40_1","article-title":"Language Models Are Unsupervised Multitask Learners","volume":"1","author":"Radford A.","year":"2019","journal-title":"OpenAI Blog"},{"key":"e_1_2_15_41_1","doi-asserted-by":"crossref","unstructured":"J.HowardandS.Ruder \u201cUniversal Language Model Fine\u2010Tuning for Text Classification \u201d2018 arXiv Preprint arXiv:1801.06146.","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_2_15_42_1","unstructured":"IBM \u201cSALMON Code Repository \u201d2023 GitHub https:\/\/github.com\/IBM\/SALMON."},{"key":"e_1_2_15_43_1","unstructured":"Deep\u2010Info \u201cSALMONN Code Repository \u201d2023 GitHub https:\/\/github.com\/deep\u2010info\/SALMONN."},{"key":"e_1_2_15_44_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12544-025-00732-x"},{"key":"e_1_2_15_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3236274"},{"key":"e_1_2_15_46_1","first-page":"1","article-title":"Advances, Opportunities and Challenges in AI\u2010Enabled Technologies for Autonomous and Connected Vehicles","author":"Murphey Y. L.","year":"2022","journal-title":"AI\u2010Enabled Technologies for Autonomous and Connected Vehicles"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T09:07:59Z","timestamp":1765012079000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70392"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":45,"journal-issue":{"issue":"27-28","published-print":{"date-parts":[[2025,12,25]]}},"alternative-id":["10.1002\/cpe.70392"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70392","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"2025-03-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70392"}}