{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:57:49Z","timestamp":1776337069090,"version":"3.51.2"},"reference-count":48,"publisher":"Elsevier BV","issue":"7","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["23JCQNJC01690"],"award-info":[{"award-number":["23JCQNJC01690"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009110","name":"Xinjiang Uygur Autonomous Region Natural Science Foundation","doi-asserted-by":"publisher","award":["2022D01D43"],"award-info":[{"award-number":["2022D01D43"]}],"id":[{"id":"10.13039\/100009110","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306210"],"award-info":[{"award-number":["62306210"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFE0116400"],"award-info":[{"award-number":["2023YFE0116400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.ipm.2026.104819","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T07:33:15Z","timestamp":1776324795000},"page":"104819","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["AMART: A multi-agent reflective framework for detecting and correcting faithfulness errors in translation"],"prefix":"10.1016","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4490-0427","authenticated-orcid":false,"given":"Jiahe","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7948-4375","authenticated-orcid":false,"given":"Shaolin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2353-5038","authenticated-orcid":false,"given":"Deyi","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104819_b1","doi-asserted-by":"crossref","unstructured":"Chen, M., Duquenne, P.-A., Andrews, P., Kao, J., Mourachko, A., Schwenk, H., & Costa-juss\u00e0, M. R. (2023). BLASER: A text-free speech-to-speech translation evaluation metric. In Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers) (pp. 9064\u20139079).","DOI":"10.18653\/v1\/2023.acl-long.504"},{"key":"10.1016\/j.ipm.2026.104819_b2","unstructured":"Chen, P., Guo, Z., Haddow, B., & Heafield, K. (2024). Iterative translation refinement with large language models. In Proceedings of the 25th annual conference of the European association for machine translation (volume 1) (pp. 181\u2013190)."},{"key":"10.1016\/j.ipm.2026.104819_b3","doi-asserted-by":"crossref","unstructured":"Chen, A., Lou, L., Chen, K., Bai, X., Xiang, Y., Yang, M., Zhao, T., & Zhang, M. (2024). DUAL-REFLECT: Enhancing large language models for reflective translation through dual learning feedback mechanisms. In Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 2: short papers) (pp. 693\u2013704).","DOI":"10.18653\/v1\/2024.acl-short.64"},{"key":"10.1016\/j.ipm.2026.104819_b4","series-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"key":"10.1016\/j.ipm.2026.104819_b5","doi-asserted-by":"crossref","unstructured":"Dale, D., Voita, E., Lam, J., Hansanti, P., Ropers, C., Kalbassi, E., Gao, C., Barrault, L., & Costa-juss\u00e0, M. (2023). Halomi: A manually annotated benchmark for multilingual hallucination and omission detection in machine translation. In Proceedings of the 2023 conference on empirical methods in natural language processing (pp. 638\u2013653).","DOI":"10.18653\/v1\/2023.emnlp-main.42"},{"key":"10.1016\/j.ipm.2026.104819_b6","doi-asserted-by":"crossref","unstructured":"Darrin, M., Staerman, G., Gomes, E. D. C., Cheung, J. C., Piantanida, P., & Colombo, P. (2024). Unsupervised layer-wise score aggregation for textual ood detection. Vol. 38, In Proceedings of the AAAI conference on artificial intelligence (pp. 17880\u201317888).","DOI":"10.1609\/aaai.v38i16.29742"},{"key":"10.1016\/j.ipm.2026.104819_b7","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1162\/tacl_a_00437","article-title":"Experts, errors, and context: A large-scale study of human evaluation for machine translation","volume":"9","author":"Freitag","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.ipm.2026.104819_b8","unstructured":"Gogoulou, E., Zahra, S., Guillou, L., D\u00fcrlich, L., & Nivre, J. (2025). Can LLMs Detect Intrinsic Hallucinations in Paraphrasing and Machine Translation?. In Proceedings of the fourth workshop on generation, evaluation and metrics (GEM2) (pp. 161\u2013177)."},{"key":"10.1016\/j.ipm.2026.104819_b9","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1162\/tacl_a_00615","article-title":"Hallucinations in large multilingual translation models","volume":"11","author":"Guerreiro","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.ipm.2026.104819_b10","doi-asserted-by":"crossref","unstructured":"Guerreiro, N. M., Colombo, P., Piantanida, P., & Martins, A. F. (2023). Optimal transport for unsupervised hallucination detection in neural machine translation. In Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: long papers) (pp. 13766\u201313784).","DOI":"10.18653\/v1\/2023.acl-long.770"},{"key":"10.1016\/j.ipm.2026.104819_b11","doi-asserted-by":"crossref","first-page":"979","DOI":"10.1162\/tacl_a_00683","article-title":"Xcomet: Transparent machine translation evaluation through fine-grained error detection","volume":"12","author":"Guerreiro","year":"2024","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.ipm.2026.104819_b12","doi-asserted-by":"crossref","unstructured":"Guerreiro, N. M., Voita, E., & Martins, A. F. (2023). Looking for a needle in a haystack: A comprehensive study of hallucinations in neural machine translation. In Proceedings of the 17th conference of the European chapter of the association for computational linguistics (pp. 1059\u20131075).","DOI":"10.18653\/v1\/2023.eacl-main.75"},{"key":"10.1016\/j.ipm.2026.104819_b13","doi-asserted-by":"crossref","unstructured":"Gunjal, A., Yin, J., & Bas, E. (2024). Detecting and preventing hallucinations in large vision language models. Vol. 38, In Proceedings of the AAAI conference on artificial intelligence (pp. 18135\u201318143).","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"10.1016\/j.ipm.2026.104819_b14","series-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025"},{"key":"10.1016\/j.ipm.2026.104819_b15","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1162\/tacl_a_00642","article-title":"Exploring human-like translation strategy with large language models","volume":"12","author":"He","year":"2024","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.ipm.2026.104819_b16","doi-asserted-by":"crossref","unstructured":"Himmi, A., Staerman, G., Picot, M., Colombo, P., & Guerreiro, N. M. (2024). Enhanced hallucination detection in neural machine translation through simple detector aggregation. In Proceedings of the 2024 conference on empirical methods in natural language processing (pp. 18573\u201318583).","DOI":"10.18653\/v1\/2024.emnlp-main.1033"},{"key":"10.1016\/j.ipm.2026.104819_b17","series-title":"Mitigating large language model hallucination with faithful finetuning","author":"Hu","year":"2024"},{"issue":"2","key":"10.1016\/j.ipm.2026.104819_b18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","year":"2025","journal-title":"ACM Transactions on Information Systems"},{"key":"10.1016\/j.ipm.2026.104819_b19","series-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"10.1016\/j.ipm.2026.104819_b20","series-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"10.1016\/j.ipm.2026.104819_b21","series-title":"Semantic entropy probes: Robust and cheap hallucination detection in llms","author":"Kossen","year":"2024"},{"key":"10.1016\/j.ipm.2026.104819_b22","doi-asserted-by":"crossref","unstructured":"Liang, T., He, Z., Jiao, W., Wang, X., Wang, Y., Wang, R., Yang, Y., Shi, S., & Tu, Z. (2024). Encouraging divergent thinking in large language models through multi-agent debate. In Proceedings of the 2024 conference on empirical methods in natural language processing (pp. 17889\u201317904).","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"10.1016\/j.ipm.2026.104819_b23","series-title":"Deepseek-v3 technical report","author":"Liu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104819_b24","unstructured":"Lommel, A., Gladkoff, S., Melby, A. K., Wright, S. E., Strandvik, I., Gasova, K., Vaasa, A., Benzo, A., Sparano, R. M., Foresi, M., et al. (2024). The multi-range theory of translation quality measurement: MQM scoring models and statistical quality control. In Proceedings of the 16th conference of the association for machine translation in the americas (volume 2: presentations) (pp. 75\u201394)."},{"key":"10.1016\/j.ipm.2026.104819_b25","series-title":"Findings of the association for computational linguistics: ACL 2024","first-page":"8801","article-title":"Error analysis prompting enables human-like translation evaluation in large language models","author":"Lu","year":"2024"},{"key":"10.1016\/j.ipm.2026.104819_b26","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume":"36","author":"Madaan","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104819_b27","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104819_b28","series-title":"Findings of the association for computational linguistics: EMNLP 2023","first-page":"5622","article-title":"Towards making the most of chatgpt for machine translation","author":"Peng","year":"2023"},{"key":"10.1016\/j.ipm.2026.104819_b29","doi-asserted-by":"crossref","unstructured":"Rei, R., De Souza, J. G., Alves, D., Zerva, C., Farinha, A. C., Glushkova, T., Lavie, A., Coheur, L., & Martins, A. F. (2022). COMET-22: Unbabel-IST 2022 submission for the metrics shared task. In Proceedings of the seventh conference on machine translation (pp. 578\u2013585).","DOI":"10.18653\/v1\/2022.wmt-1.52"},{"key":"10.1016\/j.ipm.2026.104819_b30","doi-asserted-by":"crossref","unstructured":"Sellam, T., Das, D., & Parikh, A. (2020). BLEURT: Learning robust metrics for text generation. In Proceedings of the 58th annual meeting of the association for computational linguistics (pp. 7881\u20137892).","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"10.1016\/j.ipm.2026.104819_b31","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume":"36","author":"Shinn","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"10.1016\/j.ipm.2026.104819_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103277","article-title":"Measuring and mitigating language model biases in abusive language detection","volume":"60","author":"Song","year":"2023","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104819_b33","series-title":"ICASSP 2025-2025 IEEE international conference on acoustics, speech and signal processing","first-page":"1","article-title":"Towards detecting llms hallucination via markov chain-based multi-agent debate framework","author":"Sun","year":"2025"},{"key":"10.1016\/j.ipm.2026.104819_b34","doi-asserted-by":"crossref","unstructured":"Tang, Z., Chatterjee, R., & Garg, S. (2025). Mitigating hallucinated translations in large language models with hallucination-focused preference optimization. In Proceedings of the 2025 conference of the nations of the americas chapter of the association for computational linguistics: human language technologies (volume 1: long papers) (pp. 3410\u20133433).","DOI":"10.18653\/v1\/2025.naacl-long.175"},{"key":"10.1016\/j.ipm.2026.104819_b35","series-title":"Claude 3.7 sonnet system card","author":"team","year":"2025"},{"key":"10.1016\/j.ipm.2026.104819_b36","series-title":"Gemma 3 technical report","author":"Team","year":"2025"},{"key":"10.1016\/j.ipm.2026.104819_b37","series-title":"A comprehensive survey of hallucination mitigation techniques in large language models","author":"Tonmoy","year":"2024"},{"key":"10.1016\/j.ipm.2026.104819_b38","doi-asserted-by":"crossref","unstructured":"Wang, B., Deng, X., & Sun, H. (2022). Iteratively prompt pre-trained language models for chain of thought. In Proceedings of the 2022 conference on empirical methods in natural language processing (pp. 2714\u20132730).","DOI":"10.18653\/v1\/2022.emnlp-main.174"},{"key":"10.1016\/j.ipm.2026.104819_b39","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104819_b40","unstructured":"White, J. S., O\u2019Connell, T. A., & O\u2019Mara, F. E. (1994). The ARPA MT evaluation methodologies: evolution, lessons, and future approaches. In Proceedings of the first conference of the association for machine translation in the americas."},{"key":"10.1016\/j.ipm.2026.104819_b41","series-title":"Qwen2.5 technical report","author":"Yang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104819_b42","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.ipm.2026.104819_b43","doi-asserted-by":"crossref","unstructured":"Zeng, J., Meng, F., Yin, Y. Zhou, J. (2024). Teaching large language models to translate with comparison. Vol. 38, In Proceedings of the AAAI conference on artificial intelligence (pp. 19488\u201319496).","DOI":"10.1609\/aaai.v38i17.29920"},{"key":"10.1016\/j.ipm.2026.104819_b44","series-title":"Findings of the association for computational linguistics: ACL 2024","first-page":"13816","article-title":"Paying more attention to source context: Mitigating unfaithful translations from large language model","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ipm.2026.104819_b45","first-page":"123846","article-title":"Can language models perform robust reasoning in chain-of-thought prompting with noisy rationales?","volume":"37","author":"Zhou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"10.1016\/j.ipm.2026.104819_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104078","article-title":"Overcoming language barriers via machine translation with sparse mixture-of-experts fusion of large language models","volume":"62","author":"Zhu","year":"2025","journal-title":"Information Processing & Management"},{"issue":"5","key":"10.1016\/j.ipm.2026.104819_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103825","article-title":"FEDS-ICL: Enhancing translation ability and efficiency of large language model by optimizing demonstration selection","volume":"61","author":"Zhu","year":"2024","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104819_b48","series-title":"Multilingual large language models: A systematic survey","author":"Zhu","year":"2024"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326002104?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326002104?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:11:57Z","timestamp":1776334317000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326002104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":48,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["S0306457326002104"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104819","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"AMART: A multi-agent reflective framework for detecting and correcting faithfulness errors in translation","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104819","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104819"}}