{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T02:14:39Z","timestamp":1783390479747,"version":"3.54.6"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032295316","type":"print"},{"value":"9783032295323","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-29532-3_9","type":"book-chapter","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T08:46:12Z","timestamp":1783068372000},"page":"109-119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Filtering for\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Ryan","family":"Marinelli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,4]]},"reference":[{"key":"9_CR1","unstructured":"Anthropic: CCAI public comparison 2023. Technical report, Anthropic (2023). https:\/\/www-cdn.anthropic.com\/65408ee2b9c99abe53e432f300e7f43ef69fb6e4\/CCAI_public_comparison_2023.pdf"},{"key":"9_CR2","unstructured":"Bai, Y., et\u00a0al.: Constitutional AI: Harmlessness from AI feedback. arXiv preprint arXiv:2212.08073 (2022). https:\/\/arxiv.org\/abs\/2212.08073"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Bhardwaj, R., Anh, D.D., Poria, S.: Language models are homer Simpson! Safety re-alignment of fine-tuned language models through task arithmetic (2024). https:\/\/arxiv.org\/abs\/2402.11746","DOI":"10.18653\/v1\/2024.acl-long.762"},{"key":"9_CR4","unstructured":"Chen, C., Shu, K.: Can LLM-generated misinformation be detected? (2024). https:\/\/arxiv.org\/abs\/2309.13788"},{"key":"9_CR5","unstructured":"Chen, Z., et\u00a0al.: Iteralign: iterative constitutional alignment of large language models. arXiv preprint arXiv:2403.18341 (2024). https:\/\/arxiv.org\/abs\/2403.18341"},{"key":"9_CR6","unstructured":"deepset: prompt-injections: A dataset for prompt injection attacks (2023). https:\/\/huggingface.co\/datasets\/deepset\/prompt-injections. Accessed 20 Jan 2025"},{"key":"9_CR7","unstructured":"Google Threat Intelligence Group: Adversarial misuse of generative AI. Technical report, Google (2025). https:\/\/blog.google\/innovation-and-ai\/technology\/safety-security\/google-threat-intelligence-group-report-ai-november-2025\/"},{"key":"9_CR8","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: DeBERTa: decoding-enhanced BERT with disentangled attention (2021). https:\/\/arxiv.org\/abs\/2006.03654"},{"key":"9_CR9","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. CoRR abs\/1910.13461 (2019). http:\/\/arxiv.org\/abs\/1910.13461"},{"key":"9_CR10","unstructured":"Marinelli, R.: risk_cal (2025). https:\/\/github.com\/rymarinelli\/risk_cal. Accessed 01 Apr 2025"},{"key":"9_CR11","unstructured":"Meta: Adversarial threat report, first quarter 2025. Technical report, Meta Platforms (2025). https:\/\/transparency.meta.com\/integrity-reports-q1-2025"},{"key":"9_CR12","unstructured":"News API: News API (2025). https:\/\/newsapi.org\/. Accessed 2 Mar 2025"},{"key":"9_CR13","unstructured":"OpenAI: Disrupting malicious uses of our models: February 2025 update (2025). https:\/\/cdn.openai.com\/threat-intelligence-reports\/disrupting-malicious-uses-of-our-models-february-2025-update.pdf. Accessed 2 Mar 2025"},{"key":"9_CR14","unstructured":"Qi, X., et al.: Fine-tuning aligned language models compromises safety, even when users do not intend to! (2023). https:\/\/arxiv.org\/abs\/2310.03693"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Radivojevic, K., Clark, N., Brenner, P.: LLMs among us: generative AI participating in digital discourse. arXiv preprint arXiv:2402.07940v1 (2024)","DOI":"10.1609\/aaaiss.v3i1.31202"},{"key":"9_CR16","unstructured":"Sentence-Transformers: sentence-transformers\/all-minilm-l6-v2 (2025). https:\/\/huggingface.co\/sentence-transformers\/all-MiniLM-L6-v2. Accessed 2 Mar 2025"},{"key":"9_CR17","unstructured":"Shen, M., Das, S., Greenewald, K., Sattigeri, P., Wornell, G., Ghosh, S.: Thermometer: towards universal calibration for large language models (2024). https:\/\/arxiv.org\/abs\/2403.08819"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29532-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T01:50:06Z","timestamp":1783389006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29532-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,4]]},"ISBN":["9783032295316","9783032295323"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29532-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,4]]},"assertion":[{"value":"4 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Trondheim","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ntnu.edu\/nldb2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}