{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:45:02Z","timestamp":1763923502733,"version":"build-2065373602"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Google.org and Silicon Valley Community Foundation","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EPJ Data Sci."],"DOI":"10.1140\/epjds\/s13688-025-00592-4","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T10:30:59Z","timestamp":1762338659000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Conversational complexity for assessing risk in large language models"],"prefix":"10.1140","volume":"14","author":[{"given":"John","family":"Burden","sequence":"first","affiliation":[]},{"given":"Manuel","family":"Cebrian","sequence":"additional","affiliation":[]},{"given":"Jose","family":"Hernandez-Orallo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"issue":"4","key":"592_CR1","doi-asserted-by":"publisher","first-page":"367","DOI":"10.4310\/CIS.2005.v5.n4.a1","volume":"5","author":"M Alfonseca","year":"2005","unstructured":"Alfonseca M, Cebri\u00e1n M, Ortega A (2005) Common pitfalls using the normalized compression distance: what to watch out for in a compressor. Commun Inf Syst 5(4):367\u2013384","journal-title":"Commun Inf Syst"},{"key":"592_CR2","unstructured":"Anil C, Durmus E, Sharma M, Benton J, Kundu S, Batson J, Rimsky N, Tong M, Mu J, Ford D, et al (2024) Many-shot jailbreaking. Anthropic, April"},{"key":"592_CR3","unstructured":"Anthropic (2023). Hh-rlhf: codebase for rlhf (reinforcement learning from human feedback)"},{"issue":"34","key":"592_CR4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2206992119","volume":"119","author":"S Atir","year":"2022","unstructured":"Atir S, Wald KA, Epley N (2022) Talking with strangers is surprisingly informative. Proc Natl Acad Sci USA 119(34):e2206992119","journal-title":"Proc Natl Acad Sci USA"},{"key":"592_CR5","unstructured":"Bai Y, Kadavath S, Kundu S, Askell A, Kernion J, Jones A, Chen A, Goldie A, Mirhoseini A, McKinnon C, et al (2022) Constitutional ai: harmlessness from ai feedback. arXiv preprint. arXiv:2212.08073"},{"key":"592_CR6","doi-asserted-by":"publisher","first-page":"11","DOI":"10.18653\/v1\/2022.emnlp-tutorials.3","volume-title":"Proceedings of the 2022 conference on empirical methods in natural language processing: tutorial abstracts","author":"M Baroni","year":"2022","unstructured":"Baroni M, Dess\u00ec R, Lazaridou A (2022) Emergent language-based coordination in deep multi-agent systems. In: Proceedings of the 2022 conference on empirical methods in natural language processing: tutorial abstracts, pp\u00a011\u201316"},{"key":"592_CR7","unstructured":"Bellard F (2019) Lossless data compression with neural networks. https:\/\/bellard.org\/nncp\/nncp.pdf"},{"key":"592_CR8","unstructured":"Bergey CA, DeDeo S (2024) From \u201cum\u201d to \u201cyeah\u201d: producing, predicting, and regulating information flow in human conversation. arXiv preprint. arXiv:2403.08890"},{"key":"592_CR9","unstructured":"Bhardwaj R, Poria S (2023) Red-teaming large language models using chain of utterances for safety-alignment. arXiv preprint. arXiv:2308.09662"},{"key":"592_CR10","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, et al. (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"issue":"6641","key":"592_CR11","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1126\/science.adf6369","volume":"380","author":"R Burnell","year":"2023","unstructured":"Burnell R, Schellaert W, Burden J, Ullman TD, Martinez-Plumed F, Tenenbaum JB, Rutar D, Cheke LG, Sohl-Dickstein J, Mitchell M, Kiela D, Shanahan M, Voorhees EM, Cohn AG, Leibo JZ, Hernandez-Orallo J (2023) Rethink reporting of evaluation results in AI. Science 380(6641):136\u2013138","journal-title":"Science"},{"key":"592_CR12","unstructured":"Carlini N, Nasr M, Choquette-Choo CA, Jagielski M, Gao I, Awadalla A, Koh PW, Ippolito D, Lee K, Tramer F, et al (2023) Are aligned neural networks adversarially aligned? arXiv preprint. arXiv:2306.15447"},{"issue":"2","key":"592_CR13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.60.1412","volume":"60","author":"JM Carlson","year":"1999","unstructured":"Carlson JM, Doyle J (1999) Highly optimized tolerance: a mechanism for power laws in designed systems. Phys Rev E 60(2):1412","journal-title":"Phys Rev E"},{"issue":"5","key":"592_CR14","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1109\/TIT.2007.894669","volume":"53","author":"M Cebri\u00e1n","year":"2007","unstructured":"Cebri\u00e1n M, Alfonseca M, Ortega A (2007) The normalized compression distance is resistant to noise. IEEE Trans Inf Theory 53(5):1895\u20131900","journal-title":"IEEE Trans Inf Theory"},{"issue":"4","key":"592_CR15","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1145\/321356.321363","volume":"13","author":"GJ Chaitin","year":"1966","unstructured":"Chaitin GJ (1966) On the length of programs for computing finite binary sequences. J ACM 13(4):547\u2013569","journal-title":"J ACM"},{"issue":"3","key":"592_CR16","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/TKDE.2007.48","volume":"19","author":"RL Cilibrasi","year":"2007","unstructured":"Cilibrasi RL, Vitanyi PM (2007) The Google similarity distance. IEEE Trans Knowl Data Eng 19(3):370\u2013383","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"592_CR17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.83.036115","volume":"83","author":"B Corominas-Murtra","year":"2011","unstructured":"Corominas-Murtra B, Fortuny J, Sol\u00e9 RV (2011) Emergence of Zipf\u2019s law in the evolution of communication. Phys Rev E, Stat Nonlinear Soft Matter Phys 83(3):036115","journal-title":"Phys Rev E, Stat Nonlinear Soft Matter Phys"},{"issue":"1","key":"592_CR18","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1111\/j.1468-2958.1985.tb00065.x","volume":"12","author":"JA Daly","year":"1985","unstructured":"Daly JA, Bell RA, Glenn PJ, Lawrence S (1985) Conceptualizing conversational complexity. Hum Commun Res 12(1):30\u201353","journal-title":"Hum Commun Res"},{"key":"592_CR19","unstructured":"Del\u00e9tang G, Ruoss A, Duquenne P-A, Catt E, Genewein T, Mattern C, Grau-Moya J, Wenliang LK, Aitchison M, Orseau L, et al (2023) Language modeling is compression. arXiv preprint. arXiv:2309.10668"},{"key":"592_CR20","doi-asserted-by":"crossref","unstructured":"Deng G, Liu Y, Li Y, Wang K, Zhang Y, Li Z, Wang H, Zhang T, Liu Y (2023) Jailbreaker: automated jailbreak across multiple large language model chatbots. arXiv preprint. arXiv:2307.08715","DOI":"10.14722\/ndss.2024.24188"},{"key":"592_CR21","unstructured":"Elmoznino E, Jiralerspong T, Bengio Y, Lajoie G (2024) A complexity-based theory of compositionality. arXiv preprint. arXiv:2410.14817"},{"key":"592_CR22","unstructured":"Feng G, Gu Y, Zhang B, Ye H, He D, Wang L (2023) Towards revealing the mystery behind chain of thought: a theoretical perspective. arXiv preprint. arXiv:2305.15408"},{"key":"592_CR23","unstructured":"Ganguli D, Lovitt L, Kernion J, Askell A, Bai Y, Kadavath S, Mann B, Perez E, Schiefer N, Ndousse K, et al (2022) Red teaming language models to reduce harms: methods, scaling behaviors, and lessons learned. arXiv preprint. arXiv:2209.07858"},{"key":"592_CR24","unstructured":"Glukhov D, Shumailov I, Gal Y, Papernot N, Papyan V (2023) Llm censorship: a machine learning challenge or a computer security problem? arXiv preprint. arXiv:2307.10719"},{"key":"592_CR25","unstructured":"Intelligence H (2024) Generative AI red teaming challenge: transparency report. Technical report, Humane Intelligence. Findings from the largest-ever Generative AI Public red teaming event for closed-source API models, held at DEFCON 2023"},{"key":"592_CR26","unstructured":"Kinniment M, Sato LJK, Du H, Goodrich B, Hasin M, Chan L, Miles LH, Lin TR, Wijk H, Burget J, et al (2023) Evaluating language-model agents on realistic autonomous tasks. arXiv preprint. arXiv:2312.11671"},{"issue":"6798","key":"592_CR27","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1038\/35022643","volume":"406","author":"JM Kleinberg","year":"2000","unstructured":"Kleinberg JM (2000) Navigation in a small world. Nature 406(6798):845\u2013845","journal-title":"Nature"},{"issue":"1","key":"592_CR28","first-page":"1","volume":"1","author":"AN Kolmogorov","year":"1965","unstructured":"Kolmogorov AN (1965) Three approaches to the quantitative definition of information. Probl Inf Transm 1(1):1\u20137","journal-title":"Probl Inf Transm"},{"issue":"3","key":"592_CR29","first-page":"115","volume":"9","author":"LA Levin","year":"1973","unstructured":"Levin LA (1973) Universal sequential search problems. Probl Pereda Inf 9(3):115\u2013116","journal-title":"Probl Pereda Inf"},{"key":"592_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11298-1","volume-title":"An introduction to Kolmogorov complexity and its applications","author":"M Li","year":"2019","unstructured":"Li M, Vit\u00e1nyi P, et al. (2019) An introduction to Kolmogorov complexity and its applications, vol\u00a03, 4th edn. Springer, Berlin","edition":"4"},{"key":"592_CR31","first-page":"1950","volume":"35","author":"H Liu","year":"2022","unstructured":"Liu H, Tam D, Muqeeth M, Mohta J, Huang T, Bansal M, Raffel CA (2022) Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Adv Neural Inf Process Syst 35:1950\u20131965","journal-title":"Adv Neural Inf Process Syst"},{"key":"592_CR32","doi-asserted-by":"crossref","unstructured":"Liu Y, Deng G, Xu Z, Li Y, Zheng Y, Zhang Y, Zhao L, Zhang T, Liu Y (2023). Jailbreaking chatgpt via prompt engineering: an empirical study","DOI":"10.1145\/3663530.3665021"},{"key":"592_CR33","volume-title":"Information theory, inference and learning algorithms","author":"DJ MacKay","year":"2003","unstructured":"MacKay DJ (2003) Information theory, inference and learning algorithms. Cambridge University Press, Cambridge"},{"key":"592_CR34","doi-asserted-by":"publisher","DOI":"10.1515\/9781400841356","volume-title":"The structure and dynamics of networks","author":"M Newman","year":"2011","unstructured":"Newman M, Barab\u00e1si A-L, Watts DJ (2011) The structure and dynamics of networks. Princeton University Press, Princeton"},{"key":"592_CR35","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C, Mishkin P, Zhang C, Agarwal S, Slama K, Ray A, et al. (2022) Training language models to follow instructions with human feedback. Adv Neural Inf Process Syst 35:27730\u201327744","journal-title":"Adv Neural Inf Process Syst"},{"key":"592_CR36","doi-asserted-by":"crossref","unstructured":"Perez E, Huang S, Song F, Cai T, Ring R, Aslanides J, Glaese A, McAleese N, Irving G (2022) Red teaming language models with language models. arXiv preprint. arXiv:2202.03286","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"key":"592_CR37","unstructured":"Phuong M, Aitchison M, Catt E, Cogan S, Kaskasoli A, Krakovna V, Lindner D, Rahtz M, Assael Y, Hodkinson S, et al (2024) Evaluating frontier models for dangerous capabilities. arXiv preprint. arXiv:2403.13793"},{"issue":"7753","key":"592_CR38","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1038\/s41586-019-1138-y","volume":"568","author":"I Rahwan","year":"2019","unstructured":"Rahwan I, Cebrian M, Obradovich N, Bongard J, Bonnefon J-F, Breazeal C, Crandall JW, Christakis NA, Couzin ID, Jackson MO, et al. (2019) Machine behaviour. Nature 568(7753):477\u2013486","journal-title":"Nature"},{"key":"592_CR39","unstructured":"Roose K (2023) A Conversation with Bing\u2019s Chatbot Left Me Deeply Unsettled. The New York Times"},{"key":"592_CR40","unstructured":"Russinovich M, Salem A, Eldan R (2024) Great, now write an article about that: the crescendo multi-turn llm jailbreak attack. arXiv preprint. arXiv:2404.01833"},{"issue":"3","key":"592_CR41","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1038\/s42256-022-00458-8","volume":"4","author":"P Schramowski","year":"2022","unstructured":"Schramowski P, Turan C, Andersen N, Rothkopf CA, Kersting K (2022) Large pre-trained language models contain human-like biases of what is right and wrong to do. Nat Mach Intell 4(3):258\u2013268","journal-title":"Nat Mach Intell"},{"issue":"7987","key":"592_CR42","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-023-06647-8","volume":"623","author":"M Shanahan","year":"2023","unstructured":"Shanahan M, McDonell K, Reynolds L (2023) Role play with large language models. Nature 623(7987):493\u2013498","journal-title":"Nature"},{"issue":"3","key":"592_CR43","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27(3):379\u2013423","journal-title":"Bell Syst Tech J"},{"key":"592_CR44","unstructured":"Sharma M, Tong M, Korbak T, Duvenaud D, Askell A, Bowman SR, Cheng N, Durmus E, Hatfield-Dodds Z, Johnston SR, Kravec S, Maxwell T, McCandlish S, Ndousse K, Rausch O, Schiefer N, Yan D, Zhang M, Perez E (2023) Towards Understanding Sycophancy in Language Models. arXiv:2310.13548 [cs, stat]"},{"key":"592_CR45","doi-asserted-by":"crossref","unstructured":"Shi Z, Wang Y, Yin F, Chen X, Chang K-W, Hsieh C-J (2023) Red teaming language model detectors with language models. arXiv preprint. arXiv:2305.19713","DOI":"10.1162\/tacl_a_00639"},{"issue":"1","key":"592_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0019-9958(64)90223-2","volume":"7","author":"RJ Solomonoff","year":"1964","unstructured":"Solomonoff RJ (1964) A formal theory of inductive inference. Part I. Inf Control 7(1):1\u201322","journal-title":"Inf Control"},{"issue":"2","key":"592_CR47","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/S0019-9958(64)90131-7","volume":"7","author":"RJ Solomonoff","year":"1964","unstructured":"Solomonoff RJ (1964) A formal theory of inductive inference. Part II. Inf Control 7(2):224\u2013254","journal-title":"Inf Control"},{"key":"592_CR48","doi-asserted-by":"crossref","unstructured":"Sun H, Xu G, Deng J, Cheng J, Zheng C, Zhou H, Peng N, Zhu X, Huang M (2021) On the safety of conversational models: taxonomy, dataset, and benchmark. arXiv preprint. arXiv:2110.08466","DOI":"10.18653\/v1\/2022.findings-acl.308"},{"key":"592_CR49","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, Bashlykov N, Batra S, Bhargava P, Bhosale S, et al (2023) Llama 2: open foundation and fine-tuned chat models. arXiv preprint. arXiv:2307.09288"},{"key":"592_CR50","unstructured":"Weidinger L, Mellor J, Rauh M, Griffin C, Uesato J, Huang P-S, Cheng M, Glaese M, Balle B, Kasirzadeh A, et al (2021) Ethical and social risks of harm from language models. arXiv preprint. arXiv:2112.04359"},{"issue":"43","key":"592_CR51","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2310223120","volume":"120","author":"ML Wong","year":"2023","unstructured":"Wong ML, Cleland CE, Arend D Jr, Bartlett S, Cleaves HJ, Demarest H, Prabhu A, Lunine JI, Hazen RM (2023) On the roles of function and selection in evolving systems. Proc Natl Acad Sci USA 120(43):e2310223120","journal-title":"Proc Natl Acad Sci USA"},{"key":"592_CR52","doi-asserted-by":"crossref","unstructured":"Xu J, Ma MD, Wang F, Xiao C, Chen M (2023) Instructions as backdoors: backdoor vulnerabilities of instruction tuning for large language models. arXiv preprint. arXiv:2305.14710","DOI":"10.18653\/v1\/2024.naacl-long.171"},{"key":"592_CR53","first-page":"1","volume-title":"Proceedings of the 13th conference on creativity and cognition","author":"P Yanardag","year":"2021","unstructured":"Yanardag P, Cebrian M, Rahwan I (2021) Shelley: a crowd-sourced collaborative horror writer. In: Proceedings of the 13th conference on creativity and cognition, pp\u00a01\u20138"},{"key":"592_CR54","doi-asserted-by":"crossref","unstructured":"Ye X, Iyer S, Celikyilmaz A, Stoyanov V, Durrett G, Pasunuru R (2023). Complementary explanations for effective in-context learning","DOI":"10.18653\/v1\/2023.findings-acl.273"},{"issue":"6","key":"592_CR55","doi-asserted-by":"publisher","DOI":"10.3390\/e22060612","volume":"22","author":"H Zenil","year":"2020","unstructured":"Zenil H (2020) A review of methods for estimating algorithmic complexity: options, challenges, and new directions. Entropy 22(6):612","journal-title":"Entropy"},{"key":"592_CR56","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-64985-5","volume-title":"Methods and applications of algorithmic complexity: beyond statistical lossless compression","author":"H Zenil","year":"2022","unstructured":"Zenil H, Toscano FS, Gauvrit N (2022) Methods and applications of algorithmic complexity: beyond statistical lossless compression, vol\u00a044. Springer, Berlin"}],"container-title":["EPJ Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1140\/epjds\/s13688-025-00592-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1140\/epjds\/s13688-025-00592-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1140\/epjds\/s13688-025-00592-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T23:02:28Z","timestamp":1762383748000},"score":1,"resource":{"primary":{"URL":"https:\/\/epjdatascience.springeropen.com\/articles\/10.1140\/epjds\/s13688-025-00592-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["592"],"URL":"https:\/\/doi.org\/10.1140\/epjds\/s13688-025-00592-4","relation":{},"ISSN":["2193-1127"],"issn-type":[{"type":"electronic","value":"2193-1127"}],"subject":[],"published":{"date-parts":[[2025,11,5]]},"assertion":[{"value":"24 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Provided by all authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"78"}}