{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T16:13:31Z","timestamp":1768407211961,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819794331","type":"print"},{"value":"9789819794348","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-9434-8_34","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"437-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SafeLLMs: A Benchmark for\u00a0Secure Bilingual Evaluation of\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Wenhan","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijia","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhu","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaofeng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"34_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"34_CR2","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"34_CR3","unstructured":"Bhardwaj, R., Poria, S.: Red-teaming large language models using chain of utterances for safety-alignment. arXiv preprint arXiv:2308.09662 (2023)"},{"key":"34_CR4","unstructured":"Chen, M., D\u2019Arcy, M., Liu, A., Fernandez, J., Downey, D.: Codah: an adversarially authored question-answer dataset for common sense. arXiv preprint arXiv:1904.04365 (2019)"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Davidson, T., Warmsley, D., Macy, M., Weber, I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 11, pp. 512\u2013515 (2017)","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"De\u00a0Gibert, O., Perez, N., Garc\u00eda-Pablos, A., Cuadros, M.: Hate speech dataset from a white supremacy forum. arXiv preprint arXiv:1809.04444 (2018)","DOI":"10.18653\/v1\/W18-5102"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., et al. Cold: a benchmark for Chinese offensive language detection. arXiv preprint arXiv:2201.06025 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.796"},{"key":"34_CR8","unstructured":"Duan, S., Yi, X., Zhang, P., Lu, T., Xie, X., Gu, N.: Denevil: towards deciphering and navigating the ethical values of large language models via instruction learning. arXiv preprint arXiv:2310.11053, 2023"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Gehman, S., Gururangan, S., Sap, M., Choi, Y., Smith, N.A.: RealToxicityPrompts: evaluating neural toxic degeneration in language models. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 3356\u20133369. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"34_CR10","unstructured":"Hendrycks, D., et al.: Aligning ai with shared human values. arXiv preprint arXiv:2008.02275 (2020)"},{"key":"34_CR11","unstructured":"Huang, Y., Zhang, Q., Sun, L., et\u00a0al.: Trustgpt: a benchmark for trustworthy and responsible large language models. arXiv preprint arXiv:2306.11507 (2023)"},{"key":"34_CR12","unstructured":"Jiang, L., et\u00a0al.: Can machines learn morality? the delphi experiment. arXiv preprint arXiv:2110.07574 (2021)"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Lee, N., et al.: Llm2llm: boosting llms with novel iterative data enhancement. arXiv preprint arXiv:2403.15042 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.388"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Levy, S., et al.: Safetext: a benchmark for exploring physical safety in language models. arXiv preprint arXiv:2210.10045 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.154"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Multi-step jailbreaking privacy attacks on chatgpt (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.272"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, X., Zhao, W.X., Nie, J.Y., Wen, J.R.: Halueval: a large-scale hallucination evaluation benchmark for large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 6449\u20136464 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"34_CR17","unstructured":"Liu, Y., et al.: Trustworthy llms: a survey and guideline for evaluating large language models\u2019 alignment. arXiv preprint arXiv:2308.05374 (2023)"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Lourie, N., Le Bras, R., Choi, Y.: Scruples: a corpus of community ethical judgments on 32,000 real-life anecdotes. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 13470\u201313479 (2021)","DOI":"10.1609\/aaai.v35i15.17589"},{"key":"34_CR19","unstructured":"Neel, S., Chang, P.: Privacy issues in large language models: a survey. arXiv preprint arXiv:2312.06717 (2023)"},{"key":"34_CR20","unstructured":"Qiu, H., Zhang, S., Li, A., He, H., Lan, Z.: Latent jailbreak: a benchmark for evaluating text safety and output robustness of large language models. arXiv preprint arXiv:2307.08487 (2023)"},{"key":"34_CR21","unstructured":"Sun, H., Zhang, Z., Deng, J., Cheng, J., Huang, M.: Safety assessment of Chinese large language models (2023)"},{"key":"34_CR22","unstructured":"Sun, L., et\u00a0al.: Trustllm: trustworthiness in large language models. arXiv preprint arXiv:2401.05561 (2024)"},{"key":"34_CR23","unstructured":"Wang, B., et\u00a0al.: Decodingtrust: a comprehensive assessment of trustworthiness in gpt models. arXiv preprint arXiv:2306.11698 (2023)"},{"key":"34_CR24","unstructured":"Wang, C., et\u00a0al.: Survey on factuality in large language models: knowledge, retrieval and domain-specificity. arXiv preprint arXiv:2310.07521 (2023)"},{"key":"34_CR25","unstructured":"Wang, Y., Li, H., Han, X., Nakov, P., Baldwin, T.: Do-not-answer: a dataset for evaluating safeguards in llms. arXiv preprint arXiv:2308.13387 (2023)"},{"key":"34_CR26","unstructured":"Xu, G., et\u00a0al.: Cvalues: measuring the values of Chinese large language models from safety to responsibility. arXiv preprint arXiv:2307.09705 (2023)"},{"key":"34_CR27","unstructured":"Xu, L., Zhao, K., Zhu, L., Xue, H.: Sc-safety: a multi-round open-ended question adversarial safety benchmark for large language models in Chinese. arXiv preprint arXiv:2310.05818 (2023)"},{"key":"34_CR28","unstructured":"Jintang Xue, Yun-Cheng Wang, Chengwei Wei, Xiaofeng Liu, Jonghye Woo, and C-C\u00a0Jay Kuo. Bias and fairness in chatbots: An overview. arXiv preprint arXiv:2309.08836, 2023"},{"key":"34_CR29","unstructured":"Zhang, Z., et al.: Safetybench: evaluating the safety of large language models with multiple choice questions. arXiv preprint arXiv:2309.07045 (2023)"},{"key":"34_CR30","unstructured":"Zhao, J., Fang, M., Pan, S., Yin, W., Pechenizkiy, M.: Gptbias: a comprehensive framework for evaluating bias in large language models. arXiv preprint arXiv:2312.06315 (2023)"},{"key":"34_CR31","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: Towards identifying social bias in dialog systems: framework, dataset, and benchmark. In Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 3576\u20133591 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.262"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9434-8_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:39:18Z","timestamp":1730385558000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9434-8_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794331","9789819794348"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9434-8_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}