{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:04Z","timestamp":1774419964598,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888481","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Hallucinations on Object Attributes using Multiview Images and Negative Instructions"],"prefix":"10.1109","author":[{"given":"Zhijie","family":"Tan","sequence":"first","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhi","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengwei","family":"Meng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Computer Science,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Mo","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingce","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Chu","sequence":"additional","affiliation":[{"name":"Peking University,School of Software and Microelectronics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Large language models are visual reasoning coordinators","volume":"36","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_23"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref5","author":"Fadeeva","year":"2024","journal-title":"Representing online handwriting for recognition in large vision-language models"},{"key":"ref6","author":"Tan","year":"2023","journal-title":"Building a modal-balanced blockchain with semantic reconstruction"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.54254\/2755-2721\/2024.17851"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref9","author":"Rawte","year":"2023","journal-title":"A survey of hallucination in large foundation models"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref12","author":"Wang","year":"2023","journal-title":"An llm-free multi-dimensional benchmark for mllms hallucination evaluation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548205"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01813"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475391"},{"key":"ref17","author":"Hu","year":"2023","journal-title":"Ciem: Contrastive instruction evaluation method for better instruction tuning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.4"},{"key":"ref19","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu"},{"key":"ref20","author":"You","year":"2023","journal-title":"Ferret: Refer and ground anything anywhere at any granularity"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"ref22","article-title":"One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02086"},{"key":"ref24","author":"Lu","year":"2023","journal-title":"Can sam boost video super-resolution?"},{"key":"ref25","article-title":"Hierarchical open-vocabulary universal image segmentation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","author":"Tan","year":"2024","journal-title":"Order matters: Exploring order sensitivity in multimodal large language models"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00100"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"ref30","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00039"},{"key":"ref32","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref33","author":"Young","year":"2024","journal-title":"Yi: Open foundation models by 01. ai"},{"key":"ref34","author":"Xue","year":"2024","journal-title":"xgen-mm (blip-3): A family of open large multimodal models"},{"key":"ref35","author":"Awadalla","year":"2023","journal-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01274"},{"key":"ref37","author":"Lauren\u00e7on","year":"2024","journal-title":"What matters when building vision-language models?"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888481.pdf?arnumber=10888481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:39Z","timestamp":1774416339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888481","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}