{"work":{"id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","openalex_id":"https://openalex.org/W4309674289","doi":"10.1145/3571730","arxiv_id":null,"raw_key":null,"title":"Survey of Hallucination in Natural Language Generation,","authors":[{"ORCID":"https://orcid.org/0000-0002-0206-7861","given":"Ziwei","family":"Ji","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0003-1144-1103","given":"Nayeon","family":"Lee","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-3921-3519","given":"Rita","family":"Frieske","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0001-5396-950X","given":"Tiezheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0001-5746-9545","given":"Dan","family":"Su","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0003-2205-2429","given":"Yan","family":"Xu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-6423-539X","given":"Etsuko","family":"Ishii","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-2968-0033","given":"Ye Jin","family":"Bang","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-8672-715X","given":"Andrea","family":"Madotto","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false},{"ORCID":"https://orcid.org/0000-0002-0628-7132","given":"Pascale","family":"Fung","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}],"authenticated-orcid":false}],"authors_text":"Z","year":2023,"venue":"ACM Computing Surveys","abstract":null,"external_url":"https://doi.org/10.1145/3571730","cited_by_count":2906,"metadata_source":"doi_reference","metadata_fetched_at":"2026-07-03T13:28:18.097545+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T21:34:13.397336+00:00","updated_at":"2026-07-03T13:28:18.097545+00:00","title_quality_ok":true,"display_title":"Survey of Hallucination in Natural Language Generation","render_title":"Survey of Hallucination in Natural Language Generation"},"hub":{"state":{"work_id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","tier":"super_hub","tier_reason":"100+ Pith inbound or 10,000+ external citations","pith_inbound_count":104,"external_cited_by_count":2906,"distinct_field_count":16,"first_pith_cited_at":"2023-03-15T19:31:21+00:00","last_pith_cited_at":"2026-07-02T08:07:56+00:00","author_build_status":"needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-07-06T04:08:45.505232+00:00","tier_text":"super_hub"},"tier":"super_hub","role_counts":[{"context_role":"background","n":17}],"polarity_counts":[{"context_polarity":"background","n":15},{"context_polarity":"unclear","n":2}],"runs":{"ask_index":{"job_type":"ask_index","status":"succeeded","result":{"title":"Survey of Hallucination in Natural Language Generation","claims":[{"claim_text":"intelligence summarization [4-6]. Comparable trends are evident across more general high-stakes technical domains such as healthcare, engineering, and infrastructure operations [7,8]. This increasing dependence underscores a broader shift toward AI-mediated decision-making in professional contexts. However, it also introduces risks of LLMs \"hallucinating\" [9] plausible-sounding but unfaithful or nonsensical information, which can be particularly hazardous in domains where reliability and accurac","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"KDD '26, August 9-13, 2026, Jeju, South Korea Fang and Mola, et al. 1 Introduction Many organizations, including Meta, are using Large Language Models (LLMs) to catalyze a paradigm shift in the way informa- tion is processed: moving from rigid, rule-based automation to flexible, semantic-aware intelligence [7, 9, 28]. However, there is a well-known trust gap [12] due to the inherent stochastic nature of generative AI. In particular, AI hallucination presents a severe existential risk when AI is ","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"PLOS ONE, 18(3):e0281780, 2023. doi: 10.1371/journal.pone.0281780. URLhttps://doi.org/10.1371/journal.pone.0281780. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Delong Chen, Wenliang Dai, Ho Shu Chan, Andrea Madotto, and Pascale Fung. Survey of hallucination in natural language generation.ACM Computing Surveys, 55(12):1-38, December 2023. ISSN 0360-0300, 1557-7341. doi: 10.1145/3571730. 10 Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kama","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Language Models (Mostly) Know What They Know. InarXiv preprint arXiv:2207.05221. https://arxiv.org/abs/2207.05221 [30] Harmanpreet Kaur, Daniel McDuff, Alex C Williams, Jaime Teevan, and Shamsi T Iqbal. 2022. \"I Didn't Know I Looked Angry\": Characterizing Observed Emotion and Reported Affect at Work. InCHI Conference on Human Factors in Computing Systems. 1-18. 22•Anonymous Author(s) [31] Harmanpreet Kaur, Harsha Nori, Samuel Jenkins, Rich Caruana, Hanna Wallach, and Jennifer Wortman Vaughan. 20","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"over the past few months and it has also sparked many of the prompt approaches and LLM augmentation methods we will later describe. Hallucination: In the realm of Large Language Models (LLMs), the phenomenon of \"hallucinations\" has garnered significant attention. Defined in the literature, notably in the \"Survey of Hallucination in Natural Language Generation\" paper [145], hallucination in an LLM is characterized as \"the generation of content that is nonsensical or unfaithful to the provided sou","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Runtime validation frameworks such as NeMo Guardrails [23] and Guardrails AI enforce constraints on LLM outputs through rule-based or model-based filters. These frameworks operate on the model's text output; the AIOps layer described in Section 6 operates on tool-call parameters before execution, preventing invalid queries from reaching the database rather than filtering invalid responses after the fact. Ji et al. [24] and Huang et al. [25] provide comprehensive surveys of LLM hallucination; our","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Survey of Hallucination in Natural Language Generation because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (17 contexts).","role_counts":[{"n":17,"context_role":"background"}]},"error":null,"updated_at":"2026-07-01T16:01:23.609052+00:00"},"author_expand":{"job_type":"author_expand","status":"succeeded","result":{"authors_linked":[{"id":"c63358c1-58cf-468d-890c-39fa8178d63c","orcid":null,"display_name":"Ziwei Ji"},{"id":"fecda73a-2418-4dee-9a82-60faf95e666c","orcid":null,"display_name":"Nayeon Lee"},{"id":"d2fb6c68-e493-448e-994a-31b3777d1866","orcid":null,"display_name":"Rita Frieske"},{"id":"2df02c07-7bf0-4d45-b722-6672482aa3ea","orcid":null,"display_name":"Tiezheng Yu"},{"id":"6c43fa5c-f146-4a3c-ac48-4290c6508fef","orcid":null,"display_name":"Dan Su"},{"id":"651a3c96-2c23-4ba3-b641-598f8a093bdd","orcid":null,"display_name":"Yan Xu"},{"id":"23f497a6-b58a-4558-8b26-e1ac9ae74bf8","orcid":null,"display_name":"Etsuko Ishii"},{"id":"c5e043a2-63e3-479c-974f-7b125c05079d","orcid":null,"display_name":"Ye Jin Bang"},{"id":"2dccd227-eefc-4d5b-b24a-8726711e7208","orcid":null,"display_name":"Andrea Madotto"},{"id":"93a94bc6-000b-46b0-92de-bbe1065e09dc","orcid":null,"display_name":"Pascale Fung"}]},"error":null,"updated_at":"2026-07-01T16:01:25.223076+00:00"},"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T18:19:56.973708+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","work_id":"ed8c5be1-1069-44c0-8dc4-627a7de3a371","shared_citers":8},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":7},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","shared_citers":6},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":6},{"title":"Bradley Efron and Robert J Tibshirani.An introduction to the bootstrap, volume","work_id":"414143a1-235c-49ec-a733-5cff2faefa32","shared_citers":5},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":5},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":4},{"title":"booktitle =","work_id":"3c5a795a-85bd-45a1-8e65-06a9c5641111","shared_citers":4},{"title":"Chain-of-Verification Reduces Hallucination in Large Language Models","work_id":"91048824-e8a8-42af-8ce2-8b22a900653f","shared_citers":4},{"title":"Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","work_id":"45551929-96dc-40f3-9f89-10e76731cc24","shared_citers":4},{"title":"Dense passage retrieval for open-domain question answering","work_id":"083391f8-812d-430f-8d08-89a03031ce6c","shared_citers":4},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":4},{"title":"H alu E val: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","work_id":"e6b96d1b-7944-4233-8a28-a097f26db294","shared_citers":4},{"title":"Joshi, E","work_id":"d05a9c57-9d88-473a-aa65-efb13f9dee25","shared_citers":4},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":4},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":4},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":4},{"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","shared_citers":4},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":4},{"title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","work_id":"1f8027cc-877a-494d-b9e5-a01d32d3d76f","shared_citers":4},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":4},{"title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","work_id":"62105b61-411f-46e5-970a-bd322c6adbbc","shared_citers":3},{"title":"doi: 10.18653/v1/2023.emnlp-main.741","work_id":"f952e39f-7d85-4a4f-9dd7-9da09cf2c1d8","shared_citers":3}],"time_series":[{"n":3,"year":2023},{"n":2,"year":2024},{"n":28,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:20:01.646344+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T18:19:36.100699+00:00"},"role_polarity":{"job_type":"role_polarity","status":"succeeded","result":{"title":"Survey of Hallucination in Natural Language Generation","claims":[{"claim_text":"intelligence summarization [4-6]. Comparable trends are evident across more general high-stakes technical domains such as healthcare, engineering, and infrastructure operations [7,8]. This increasing dependence underscores a broader shift toward AI-mediated decision-making in professional contexts. However, it also introduces risks of LLMs \"hallucinating\" [9] plausible-sounding but unfaithful or nonsensical information, which can be particularly hazardous in domains where reliability and accurac","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"KDD '26, August 9-13, 2026, Jeju, South Korea Fang and Mola, et al. 1 Introduction Many organizations, including Meta, are using Large Language Models (LLMs) to catalyze a paradigm shift in the way informa- tion is processed: moving from rigid, rule-based automation to flexible, semantic-aware intelligence [7, 9, 28]. However, there is a well-known trust gap [12] due to the inherent stochastic nature of generative AI. In particular, AI hallucination presents a severe existential risk when AI is ","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"PLOS ONE, 18(3):e0281780, 2023. doi: 10.1371/journal.pone.0281780. URLhttps://doi.org/10.1371/journal.pone.0281780. Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Yejin Bang, Delong Chen, Wenliang Dai, Ho Shu Chan, Andrea Madotto, and Pascale Fung. Survey of hallucination in natural language generation.ACM Computing Surveys, 55(12):1-38, December 2023. ISSN 0360-0300, 1557-7341. doi: 10.1145/3571730. 10 Zhijing Jin, Yuen Chen, Felix Leeb, Luigi Gresele, Ojasv Kama","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Language Models (Mostly) Know What They Know. InarXiv preprint arXiv:2207.05221. https://arxiv.org/abs/2207.05221 [30] Harmanpreet Kaur, Daniel McDuff, Alex C Williams, Jaime Teevan, and Shamsi T Iqbal. 2022. \"I Didn't Know I Looked Angry\": Characterizing Observed Emotion and Reported Affect at Work. InCHI Conference on Human Factors in Computing Systems. 1-18. 22•Anonymous Author(s) [31] Harmanpreet Kaur, Harsha Nori, Samuel Jenkins, Rich Caruana, Hanna Wallach, and Jennifer Wortman Vaughan. 20","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"over the past few months and it has also sparked many of the prompt approaches and LLM augmentation methods we will later describe. Hallucination: In the realm of Large Language Models (LLMs), the phenomenon of \"hallucinations\" has garnered significant attention. Defined in the literature, notably in the \"Survey of Hallucination in Natural Language Generation\" paper [145], hallucination in an LLM is characterized as \"the generation of content that is nonsensical or unfaithful to the provided sou","claim_type":"background","confidence":0.9,"evidence_strength":"citation_context"},{"claim_text":"Runtime validation frameworks such as NeMo Guardrails [23] and Guardrails AI enforce constraints on LLM outputs through rule-based or model-based filters. These frameworks operate on the model's text output; the AIOps layer described in Section 6 operates on tool-call parameters before execution, preventing invalid queries from reaching the database rather than filtering invalid responses after the fact. Ji et al. [24] and Huang et al. [25] provide comprehensive surveys of LLM hallucination; our","claim_type":"background","confidence":0.85,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Survey of Hallucination in Natural Language Generation because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (17 contexts).","role_counts":[{"n":17,"context_role":"background"}]},"error":null,"updated_at":"2026-07-01T16:01:23.612030+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus","claims":[{"claim_text":"[315, 361]. Furthermore, Liu et al. [185], Zong et al. [395] and Liu et al. [184] show that LVLMs can be easily fooled and experience a severe performance drop due to their over-reliance on the strong language prior, as well as its inferior ability to defend against inappropriate user inputs [112, 134]. Jiang et al. [138], Wang et al. [315] and Jing et al. [141] took a step forward to holistically evaluate multi-modal hallucination. What's more, when presented with multiple images, LVLMs sometim","claim_type":"background","confidence":0.75,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (1 contexts).","role_counts":[{"n":1,"context_role":"background"}]},"error":null,"updated_at":"2026-05-14T18:19:20.027810+00:00"}},"summary":{"title":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus","claims":[{"claim_text":"[315, 361]. Furthermore, Liu et al. [185], Zong et al. [395] and Liu et al. [184] show that LVLMs can be easily fooled and experience a severe performance drop due to their over-reliance on the strong language prior, as well as its inferior ability to defend against inappropriate user inputs [112, 134]. Jiang et al. [138], Wang et al. [315] and Jing et al. [141] took a step forward to holistically evaluate multi-modal hallucination. What's more, when presented with multiple images, LVLMs sometim","claim_type":"background","confidence":0.75,"evidence_strength":"citation_context"}],"why_cited":"Pith tracks Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus because it crossed a citation-hub threshold. Current citing contexts most often use it as background evidence (1 contexts).","role_counts":[{"n":1,"context_role":"background"}]},"graph":{"co_cited":[{"title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","work_id":"ed8c5be1-1069-44c0-8dc4-627a7de3a371","shared_citers":8},{"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","shared_citers":7},{"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","shared_citers":6},{"title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","work_id":"27eaec54-c105-4969-8188-da5f0fca3688","shared_citers":6},{"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","shared_citers":6},{"title":"Bradley Efron and Robert J Tibshirani.An introduction to the bootstrap, volume","work_id":"414143a1-235c-49ec-a733-5cff2faefa32","shared_citers":5},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":5},{"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","shared_citers":4},{"title":"booktitle =","work_id":"3c5a795a-85bd-45a1-8e65-06a9c5641111","shared_citers":4},{"title":"Chain-of-Verification Reduces Hallucination in Large Language Models","work_id":"91048824-e8a8-42af-8ce2-8b22a900653f","shared_citers":4},{"title":"Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","work_id":"45551929-96dc-40f3-9f89-10e76731cc24","shared_citers":4},{"title":"Dense passage retrieval for open-domain question answering","work_id":"083391f8-812d-430f-8d08-89a03031ce6c","shared_citers":4},{"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","shared_citers":4},{"title":"H alu E val: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","work_id":"e6b96d1b-7944-4233-8a28-a097f26db294","shared_citers":4},{"title":"Joshi, E","work_id":"d05a9c57-9d88-473a-aa65-efb13f9dee25","shared_citers":4},{"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","shared_citers":4},{"title":"ReAct: Synergizing Reasoning and Acting in Language Models","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","shared_citers":4},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":4},{"title":"Scaling Instruction-Finetuned Language Models","work_id":"8405abb1-7558-4fdf-af24-f4c52fa77a06","shared_citers":4},{"title":"Scaling Laws for Neural Language Models","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","shared_citers":4},{"title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","work_id":"1f8027cc-877a-494d-b9e5-a01d32d3d76f","shared_citers":4},{"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","shared_citers":4},{"title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","work_id":"62105b61-411f-46e5-970a-bd322c6adbbc","shared_citers":3},{"title":"doi: 10.18653/v1/2023.emnlp-main.741","work_id":"f952e39f-7d85-4a4f-9dd7-9da09cf2c1d8","shared_citers":3}],"time_series":[{"n":3,"year":2023},{"n":2,"year":2024},{"n":28,"year":2026}],"dependency_candidates":[]},"authors":[{"id":"2dccd227-eefc-4d5b-b24a-8726711e7208","orcid":null,"display_name":"Andrea Madotto","source":"manual","import_confidence":0.72},{"id":"6c43fa5c-f146-4a3c-ac48-4290c6508fef","orcid":null,"display_name":"Dan Su","source":"manual","import_confidence":0.72},{"id":"23f497a6-b58a-4558-8b26-e1ac9ae74bf8","orcid":null,"display_name":"Etsuko Ishii","source":"manual","import_confidence":0.72},{"id":"fecda73a-2418-4dee-9a82-60faf95e666c","orcid":null,"display_name":"Nayeon Lee","source":"manual","import_confidence":0.72},{"id":"93a94bc6-000b-46b0-92de-bbe1065e09dc","orcid":null,"display_name":"Pascale Fung","source":"manual","import_confidence":0.72},{"id":"d2fb6c68-e493-448e-994a-31b3777d1866","orcid":null,"display_name":"Rita Frieske","source":"manual","import_confidence":0.72},{"id":"2df02c07-7bf0-4d45-b722-6672482aa3ea","orcid":null,"display_name":"Tiezheng Yu","source":"manual","import_confidence":0.72},{"id":"651a3c96-2c23-4ba3-b641-598f8a093bdd","orcid":null,"display_name":"Yan Xu","source":"manual","import_confidence":0.72},{"id":"c5e043a2-63e3-479c-974f-7b125c05079d","orcid":null,"display_name":"Ye Jin Bang","source":"manual","import_confidence":0.72},{"id":"c63358c1-58cf-468d-890c-39fa8178d63c","orcid":null,"display_name":"Ziwei Ji","source":"manual","import_confidence":0.72}]}}