{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T20:58:58Z","timestamp":1777582738408,"version":"3.51.4"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ministry of Economic Development of the Russian Federation in accordance","award":["000000C313925P4G0002"],"award-info":[{"award-number":["000000C313925P4G0002"]}]},{"name":"Ivannikov Institute for System Programming of the Russian Academy of Sciences","award":["139-15-2025-011"],"award-info":[{"award-number":["139-15-2025-011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3682937","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:00:05Z","timestamp":1775851205000},"page":"59390-59408","source":"Crossref","is-referenced-by-count":0,"title":["ESQA: Event Sequences Question Answering"],"prefix":"10.1109","volume":"14","author":[{"given":"Irina","family":"Abdullaeva","sequence":"first","affiliation":[{"name":"FusionBrain Lab, Moscow, Russia"}]},{"given":"Ivan","family":"Karpukhin","sequence":"additional","affiliation":[{"name":"Sber AI Lab, Moscow, Russia"}]},{"given":"Andrei","family":"Filatov","sequence":"additional","affiliation":[{"name":"FusionBrain Lab, Moscow, Russia"}]},{"given":"Mikhail","family":"Orlov","sequence":"additional","affiliation":[{"name":"Sber AI Lab, Moscow, Russia"}]},{"given":"Viacheslav","family":"Vasilev","sequence":"additional","affiliation":[{"name":"Kandinsky Lab, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8368-537X","authenticated-orcid":false,"given":"Natalya","family":"Belova","sequence":"additional","affiliation":[{"name":"HSE University, Moscow, Russia"}]},{"given":"Denis","family":"Dimitrov","sequence":"additional","affiliation":[{"name":"Kandinsky Lab, Moscow, Russia"}]},{"given":"Andrey","family":"Kuznetsov","sequence":"additional","affiliation":[{"name":"FusionBrain Lab, Moscow, Russia"}]},{"given":"Ivan","family":"Kireev","sequence":"additional","affiliation":[{"name":"Sber AI Lab, Moscow, Russia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6196-0564","authenticated-orcid":false,"given":"Andrey V.","family":"Savchenko","sequence":"additional","affiliation":[{"name":"Sber AI Lab, Moscow, Russia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110794"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2023.102283"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau0323"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0316-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6648-6_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3107975"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219828"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526129"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3232287"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0855"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Brown"},{"key":"ref13","first-page":"1","article-title":"Jolt: Jointly learned representations of language and time-series","volume-title":"Proc. Deep Generative Models Health Workshop NeurIPS","author":"Cai"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0861"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.745"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3381"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICWR65219.2025.11006253"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/23311975.2025.2474209"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-industry.179"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3760828"},{"key":"ref21","volume-title":"Introduction to Statistics","author":"Lane","year":"2003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.171"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3122865.3122874"},{"key":"ref24","article-title":"Multivariate Hawkes processes","author":"Liniger","year":"2009"},{"key":"ref25","first-page":"6757","article-title":"The neural Hawkes process: A neurally self-modulating multivariate point process","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Mei"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2026.132771"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i27.39413"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414142"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1057"},{"key":"ref30","first-page":"17283","article-title":"Grounding language models to images for multimodal inputs and outputs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"key":"ref32","first-page":"8335","article-title":"Large language models for time series: A survey","volume-title":"Proc. Int. Joint Conf. Artif. Intell. (IJCAI)","author":"Zhang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685816"},{"key":"ref34","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref35","first-page":"5549","article-title":"TabLLM: Few-shot classification of tabular data with large language models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hegselmann"},{"key":"ref36","article-title":"Finetuned language models are zero-shot learners","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wei"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112828"},{"key":"ref38","article-title":"Towards explainable artificial intelligence in banking and financial services","author":"Hanif","year":"2021","journal-title":"arXiv:2112.08441"},{"key":"ref39","first-page":"8182","article-title":"LVLM-Intrepret: An interpretability tool for large vision-language models","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR))","author":"Ben Melech Stan"},{"key":"ref40","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref41","article-title":"OLMoASR: Open models and data for training robust speech recognition models","author":"Ngo","year":"2025","journal-title":"arXiv:2508.20869"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1134\/S1064226916040112"},{"key":"ref43","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111449"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2007.12.020"},{"key":"ref46","volume-title":"Pytorch-Lifestream Experiments","author":"Babaev","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1272"},{"key":"ref48","first-page":"1","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Ke"},{"key":"ref49","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref50","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021","journal-title":"arXiv:2103.03230"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref52","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","author":"Clark","year":"2020","journal-title":"arXiv:2003.10555"},{"key":"ref53","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"Lan","year":"2019","journal-title":"arXiv:1909.11942"},{"issue":"8","key":"ref54","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref55","first-page":"1","article-title":"Multi-time attention networks for irregularly sampled time series","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Shukla"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25876"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-023-00948-2"},{"key":"ref58","article-title":"MLEM: Generative and contrastive learning as distinct modalities for event sequences","author":"Moskvoretskii","year":"2024","journal-title":"arXiv:2401.15935"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608849"},{"key":"ref60","article-title":"HT-transformer: Event sequences classification by accumulating prefix information with history tokens","author":"Karpukhin","year":"2025","journal-title":"arXiv:2508.01474"},{"key":"ref61","first-page":"1","article-title":"Intensity-free learning of temporal point processes","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Shchur"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737428"},{"key":"ref63","first-page":"1","article-title":"CatBoost: Unbiased boosting with categorical features","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","volume":"31","author":"Ostroumova"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709268"},{"key":"ref65","first-page":"64663","article-title":"Generalized logit adjustment: Calibrating fine-tuned models by removing label bias in foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhu"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107657"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111650"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109976"},{"key":"ref69","first-page":"24991","article-title":"On embeddings for numerical features in tabular deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Gorishniy"},{"issue":"140","key":"ref70","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref72","article-title":"AI alignment: A comprehensive survey","author":"Ji","year":"2023","journal-title":"arXiv:2310.19852"},{"key":"ref73","first-page":"51778","article-title":"Evaluating the moral beliefs encoded in llms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Scherrer"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"ref75","article-title":"Scaling instruction-finetuned language models","author":"Won Chung","year":"2022","journal-title":"arXiv:2210.11416"},{"key":"ref76","volume-title":"Perspective Api: Developers","year":"2025"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.54"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.270"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.40"},{"key":"ref81","first-page":"85","article-title":"Neural temporal point processes for modelling electronic health records","volume-title":"Proc. Mach. Learn. Health","author":"Enguehard"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20729"},{"key":"ref83","first-page":"43322","article-title":"One fits all: Power general time series analysis by pretrained LM","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Zhou"},{"key":"ref84","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.2307\/2683757"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11479578.pdf?arnumber=11479578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:49:30Z","timestamp":1777405770000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11479578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3682937","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}