Localizing Factual Inconsistencies in Attributable Text Generation.

Shiyue Zhang 0001 张诗悦 Bloomberg AI University of North Carolina at Chapel Hill, NC, USA https://zhangshiyue.github.io/ https://scholar.google.com/citations?user=co9KUGQAAAAJ Shiyue Zhang Shi-Yue Zhang Shiyue Zhang 0002 张师悦 Peking University, School of Mathematical Sciences, Beijing, China https://scholar.google.com/citations?user=nu6YfFkAAAAJ https://github.com/ShiyueZhang66

Arie Cattan Paul Roit Shiyue Zhang 0001 David Wan Roee Aharoni Idan Szpektor Mohit Bansal Ido Dagan Localizing Factual Inconsistencies in Attributable Text Generation. 100-123 2026 14 Trans. Assoc. Comput. Linguistics https://doi.org/10.1162/tacl.a.598 db/journals/tacl/tacl14.html#CattanRZWASBD26 streams/journals/tacl

Ozan Irsoy Pengxiang Cheng 0001 Jennifer L. Chen Daniel Preotiuc-Pietro Shiyue Zhang 0001 Duccio Pappadopulo Improving Instruct Models for Free: A Study on Partial Adaptation. 11507-11521 2025 EMNLP https://doi.org/10.18653/v1/2025.emnlp-main.581 conf/emnlp/2025 db/conf/emnlp/emnlp2025.html#IrsoyCCPZP25 streams/conf/emnlp Bang An Shiyue Zhang 0001 Mark Dredze RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models. 5444-5474 2025 NAACL (Long Papers) https://doi.org/10.18653/v1/2025.naacl-long.281 https://aclanthology.org/2025.naacl-long.281/ conf/naacl/2025-1 db/conf/naacl/naacl2025-1.html#AnZD25 streams/conf/naacl

Ozan Irsoy Pengxiang Cheng 0001 Jennifer L. Chen Daniel Preotiuc-Pietro Shiyue Zhang 0001 Duccio Pappadopulo Improving Instruct Models for Free: A Study on Partial Adaptation. 2025 April abs/2504.11626 CoRR https://doi.org/10.48550/arXiv.2504.11626 db/journals/corr/corr2504.html#abs-2504-11626 streams/journals/corr

Bang An Shiyue Zhang 0001 Mark Dredze RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models. 2025 April abs/2504.18041 CoRR https://doi.org/10.48550/arXiv.2504.18041 db/journals/corr/corr2504.html#abs-2504-18041 streams/journals/corr

Shuyang Cao Karthik Radhakrishnan David S. Rosenberg Steven Lu 0003 Pengxiang Cheng 0001 Lu Wang 0008 Shiyue Zhang 0001 Evaluating the Retrieval Robustness of Large Language Models. 2025 May abs/2505.21870 CoRR https://doi.org/10.48550/arXiv.2505.21870 db/journals/corr/corr2505.html#abs-2505-21870 streams/journals/corr

Arie Cattan Paul Roit Shiyue Zhang 0001 David Wan Roee Aharoni Idan Szpektor Mohit Bansal Ido Dagan Localizing Factual Inconsistencies in Attributable Text Generation. 2024 abs/2410.07473 CoRR https://doi.org/10.48550/arXiv.2410.07473 db/journals/corr/corr2410.html#abs-2410-07473 streams/journals/corr

Shiyue Zhang 0001 David Wan Arie Cattan Ayal Klein Ido Dagan Mohit Bansal QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization. 2024 abs/2412.07096 CoRR https://doi.org/10.48550/arXiv.2412.07096 db/journals/corr/corr2412.html#abs-2412-07096 streams/journals/corr

Shiyue Zhang 0001 Towards Reliable and Inclusive Natural Language Generation. 2023 University of North Carolina, Chapel Hill, USA https://doi.org/10.17615/txe6-by19 https://cdr.lib.unc.edu/downloads/gh93h8798?file=thumbnail https://cdr.lib.unc.edu/downloads/gh93h8798 https://www.base-search.net/Record/4b2dd87e41f95e2517d8cda586e6b8d69df03e9544655b5579ad38b73168c135 base-search.net (ftcarolinadr:cdr.lib.unc.edu:2514nw84r) Shiyue Zhang 0001 David Wan Mohit Bansal Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization. 2153-2174 2023 ACL (1) https://doi.org/10.18653/v1/2023.acl-long.120 https://aclanthology.org/2023.acl-long.120 https://www.wikidata.org/entity/Q131458092 conf/acl/2023-1 db/conf/acl/acl2023-1.html#ZhangWB23 Derek Tam Anisha Mascarenhas Shiyue Zhang 0001 Sarah Kwan Mohit Bansal Colin Raffel Evaluating the Factual Consistency of Large Language Models Through News Summarization. 5220-5255 2023 ACL (Findings) https://doi.org/10.18653/v1/2023.findings-acl.322 https://aclanthology.org/2023.findings-acl.322 conf/acl/2023f db/conf/acl/acl2023f.html#TamMZKBR23 Shiyue Zhang 0001 Shijie Wu Ozan Irsoy Steven Lu 0003 Mohit Bansal Mark Dredze David S. Rosenberg MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies. 9027-9050 2023 ACL (1) https://doi.org/10.18653/v1/2023.acl-long.502 https://aclanthology.org/2023.acl-long.502 https://www.wikidata.org/entity/Q131458632 conf/acl/2023-1 db/conf/acl/acl2023-1.html#ZhangWILBDR23 David Wan Shiyue Zhang 0001 Mohit Bansal HistAlign: Improving Context Dependency in Language Generation by Aligning with History. 2941-2960 2023 EMNLP https://doi.org/10.18653/v1/2023.emnlp-main.179 https://aclanthology.org/2023.emnlp-main.179 conf/emnlp/2023 db/conf/emnlp/emnlp2023.html#WanZB23 Swarnadeep Saha Shiyue Zhang 0001 Peter Hase Mohit Bansal Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees. 2023 ICLR https://openreview.net/forum?id=ooxDOe7ZtBe conf/iclr/2023 db/conf/iclr/iclr2023.html#SahaZHB23

David Wan Shiyue Zhang 0001 Mohit Bansal HistAlign: Improving Context Dependency in Language Generation by Aligning with History. 2023 abs/2305.04782 CoRR https://doi.org/10.48550/arXiv.2305.04782 db/journals/corr/corr2305.html#abs-2305-04782

Shiyue Zhang 0001 Shijie Wu Ozan Irsoy Steven Lu 0003 Mohit Bansal Mark Dredze David S. Rosenberg MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies. 2023 abs/2305.16958 CoRR https://doi.org/10.48550/arXiv.2305.16958 db/journals/corr/corr2305.html#abs-2305-16958

Shiyue Zhang 0001 Benjamin Frey Mohit Bansal How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Language. 1529-1541 2022 ACL (1) https://doi.org/10.18653/v1/2022.acl-long.108 https://aclanthology.org/2022.acl-long.108 conf/acl/2022-1 db/conf/acl/acl2022-1.html#ZhangFB22 Shiyue Zhang 0001 Vishrav Chaudhary Naman Goyal 0001 James Cross 0003 Guillaume Wenzek Mohit Bansal Francisco Guzmán How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training? 97-116 2022 AMTA https://aclanthology.org/2022.amta-research.8 conf/amta/2022-1 db/conf/amta/amta2022-1.html#ZhangCGCWBG22 Xiang Zhou Shiyue Zhang 0001 Mohit Bansal Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging? 1099-1114 2022 NAACL-HLT https://doi.org/10.18653/v1/2022.naacl-main.81 https://aclanthology.org/2022.naacl-main.81 conf/naacl/2022 db/conf/naacl/naacl2022.html#ZhouZB22

Shiyue Zhang 0001 Benjamin Frey Mohit Bansal How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Language. 2022 abs/2204.11909 CoRR https://doi.org/10.48550/arXiv.2204.11909 https://www.wikidata.org/entity/Q112259355 db/journals/corr/corr2204.html#abs-2204-11909

Shiyue Zhang 0001 Vishrav Chaudhary Naman Goyal 0001 James Cross 0003 Guillaume Wenzek Mohit Bansal Francisco Guzmán How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training? 2022 abs/2204.14268 CoRR https://doi.org/10.48550/arXiv.2204.14268 db/journals/corr/corr2204.html#abs-2204-14268

Xiang Zhou Shiyue Zhang 0001 Mohit Bansal Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging? 2022 abs/2206.14969 CoRR https://doi.org/10.48550/arXiv.2206.14969 db/journals/corr/corr2206.html#abs-2206-14969

Yinuo Hu Shiyue Zhang 0001 Viji Sathy Abigail T. Panter Mohit Bansal SETSum: Summarization and Visualization of Student Evaluations of Teaching. 2022 abs/2207.03640 CoRR https://doi.org/10.48550/arXiv.2207.03640 db/journals/corr/corr2207.html#abs-2207-03640

Shiyue Zhang 0001 David Wan Mohit Bansal Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization. 2022 abs/2209.03549 CoRR https://doi.org/10.48550/arXiv.2209.03549 db/journals/corr/corr2209.html#abs-2209-03549

Swarnadeep Saha Shiyue Zhang 0001 Peter Hase Mohit Bansal Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees. 2022 abs/2209.10492 CoRR https://doi.org/10.48550/arXiv.2209.10492 db/journals/corr/corr2209.html#abs-2209-10492

Derek Tam Anisha Mascarenhas Shiyue Zhang 0001 Sarah Kwan Mohit Bansal Colin Raffel Evaluating the Factual Consistency of Large Language Models Through Summarization. 2022 abs/2211.08412 CoRR https://doi.org/10.48550/arXiv.2211.08412 db/journals/corr/corr2211.html#abs-2211-08412

Shiyue Zhang 0001 Benjamin Frey Mohit Bansal ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback. 272-279 2021 ACL (demo) https://doi.org/10.18653/v1/2021.acl-demo.33 https://aclanthology.org/2021.acl-demo.33 conf/acl/2021d db/conf/acl/acl2021-d.html#ZhangFB21 Zineng Tang Shiyue Zhang 0001 Hyounghun Kim Mohit Bansal Continuous Language Generative Flow. 4609-4622 2021 ACL/IJCNLP (1) https://doi.org/10.18653/v1/2021.acl-long.355 https://aclanthology.org/2021.acl-long.355 https://www.wikidata.org/entity/Q131458852 conf/acl/2021-1 db/conf/acl/acl2021-1.html#TangZKB20 Shiyue Zhang 0001 Asli Celikyilmaz Jianfeng Gao 0001 Mohit Bansal EmailSum: Abstractive Email Thread Summarization. 6895-6909 2021 ACL/IJCNLP (1) https://doi.org/10.18653/v1/2021.acl-long.537 https://aclanthology.org/2021.acl-long.537 conf/acl/2021-1 db/conf/acl/acl2021-1.html#ZhangCGB20 Shiyue Zhang 0001 Mohit Bansal Finding a Balanced Degree of Automation for Summary Evaluation. 6617-6632 2021 EMNLP (1) https://doi.org/10.18653/v1/2021.emnlp-main.531 https://aclanthology.org/2021.emnlp-main.531 conf/emnlp/2021-1 db/conf/emnlp/emnlp2021-1.html#ZhangB21

Shiyue Zhang 0001 Asli Celikyilmaz Jianfeng Gao 0001 Mohit Bansal EmailSum: Abstractive Email Thread Summarization. 2021 abs/2107.14691 CoRR https://arxiv.org/abs/2107.14691 db/journals/corr/corr2107.html#abs-2107-14691

Shiyue Zhang 0001 Benjamin Frey Mohit Bansal ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback. 2021 abs/2107.14800 CoRR https://arxiv.org/abs/2107.14800 db/journals/corr/corr2107.html#abs-2107-14800

Shiyue Zhang 0001 Mohit Bansal Finding a Balanced Degree of Automation for Summary Evaluation. 2021 abs/2109.11503 CoRR https://arxiv.org/abs/2109.11503 db/journals/corr/corr2109.html#abs-2109-11503

Shiyue Zhang 0001 Benjamin Frey Mohit Bansal ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization. 577-595 2020 EMNLP (1) https://doi.org/10.18653/v1/2020.emnlp-main.43 https://aclanthology.org/2020.emnlp-main.43/ conf/emnlp/2020-1 db/conf/emnlp/emnlp2020-1.html#ZhangFB20 Peter Hase Shiyue Zhang 0001 Harry Xie Mohit Bansal Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? 4351-4367 2020 EMNLP (Findings) https://doi.org/10.18653/v1/2020.findings-emnlp.390 https://aclanthology.org/2020.findings-emnlp.390/ conf/emnlp/2020f db/conf/emnlp/emnlp2020f.html#HaseZXB20

Peter Hase Shiyue Zhang 0001 Harry Xie Mohit Bansal Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? 2020 abs/2010.04119 CoRR https://arxiv.org/abs/2010.04119 db/journals/corr/corr2010.html#abs-2010-04119

Shiyue Zhang 0001 Benjamin Frey Mohit Bansal ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization. 2020 abs/2010.04791 CoRR https://arxiv.org/abs/2010.04791 db/journals/corr/corr2010.html#abs-2010-04791

Shiyue Zhang 0001 Mohit Bansal Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering. 2495-2509 2019 EMNLP/IJCNLP (1) https://doi.org/10.18653/v1/D19-1253 conf/emnlp/2019-1 db/conf/emnlp/emnlp2019-1.html#ZhangB19

Shiyue Zhang 0001 Mohit Bansal Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering. 2019 abs/1909.06356 CoRR http://arxiv.org/abs/1909.06356 db/journals/corr/corr1909.html#abs-1909-06356

Jiyuan Zhang 0001 Zheling Zhang Shiyue Zhang 0001 Dong Wang 0013 VV-Couplet: An open source Chinese couplet generation system. 1756-1760 2018 APSIPA https://doi.org/10.23919/APSIPA.2018.8659474 conf/apsipa/2018 db/conf/apsipa/apsipa2018.html#ZhangZZW18 Jiyuan Zhang 0001 Yang Feng 0004 Dong Wang 0013 Yang Wang Andrew Abel Shiyue Zhang 0001 Andi Zhang 0002 Flexible and Creative Chinese Poetry Generation Using Neural Memory. 1364-1373 2017 ACL (1) https://doi.org/10.18653/v1/P17-1125 conf/acl/2017-1 db/conf/acl/acl2017-1.html#ZhangFWWAZZ17 Shiyue Zhang 0001 Gulnigar Mahmut Dong Wang 0013 Askar Hamdulla Memory-augmented Chinese-Uyghur neural machine translation. 1092-1096 2017 APSIPA https://doi.org/10.1109/APSIPA.2017.8282190 conf/apsipa/2017 db/conf/apsipa/apsipa2017.html#ZhangMWH17 Aodong Li Shiyue Zhang 0001 Dong Wang 0013 Thomas Fang Zheng Enhanced neural machine translation by learning from draft. 1583-1587 2017 APSIPA https://doi.org/10.1109/APSIPA.2017.8282276 conf/apsipa/2017 db/conf/apsipa/apsipa2017.html#LiZWZ17 Yang Feng 0004 Shiyue Zhang 0001 Andi Zhang 0002 Dong Wang 0013 Andrew Abel Memory-augmented Neural Machine Translation. 1390-1399 2017 EMNLP https://doi.org/10.18653/v1/d17-1146 https://aclanthology.org/D17-1146/ conf/emnlp/2017 db/conf/emnlp/emnlp2017.html#FengZZWA17 Zhiyuan Tang Ying Shi 0001 Dong Wang 0013 Yang Feng 0004 Shiyue Zhang 0001 Memory visualization for gated recurrent neural networks in speech recognition. 2736-2740 2017 ICASSP https://doi.org/10.1109/ICASSP.2017.7952654 conf/icassp/2017 db/conf/icassp/icassp2017.html#TangSWFZ17 Dong Wang 0013 Thomas Fang Zheng Zhiyuan Tang Ying Shi 0001 Lantian Li Shiyue Zhang 0001 Hongzhi Yu Guanyu Li Shipeng Xu Askar Hamdulla Mijit Ablimit Gulnigar Mahmut M2ASR: Ambitions and first year progress. 1-6 2017 O-COCOSDA https://doi.org/10.1109/ICSDA.2017.8384469 conf/ococosda/2017 db/conf/ococosda/ococosda2017.html#WangZTSLZYLXHAM17

Jiyuan Zhang 0001 Yang Feng 0004 Dong Wang 0013 Yang Wang Andrew Abel Shiyue Zhang 0001 Andi Zhang 0002 Flexible and Creative Chinese Poetry Generation Using Neural Memory. 2017 abs/1705.03773 CoRR http://arxiv.org/abs/1705.03773 db/journals/corr/corr1705.html#ZhangFWWAZZ17

Shiyue Zhang 0001 Gulnigar Mahmut Dong Wang 0013 Askar Hamdulla Memory-augmented Chinese-Uyghur Neural Machine Translation. 2017 abs/1706.08683 CoRR http://arxiv.org/abs/1706.08683 db/journals/corr/corr1706.html#ZhangMWH17

Yang Feng 0004 Shiyue Zhang 0001 Andi Zhang 0002 Dong Wang 0013 Andrew Abel Memory-augmented Neural Machine Translation. 2017 abs/1708.02005 CoRR http://arxiv.org/abs/1708.02005 db/journals/corr/corr1708.html#abs-1708-02005

Aodong Li Shiyue Zhang 0001 Dong Wang 0013 Thomas Fang Zheng Enhanced Neural Machine Translation by Learning from Draft. 2017 abs/1710.01789 CoRR http://arxiv.org/abs/1710.01789 db/journals/corr/corr1710.html#abs-1710-01789

Shiyue Zhang 0001 Pengtao Xie Dong Wang 0013 Eric P. Xing Medical Diagnosis From Laboratory Tests by Combining Generative and Discriminative Learning. 2017 abs/1711.04329 CoRR http://arxiv.org/abs/1711.04329 db/journals/corr/corr1711.html#abs-1711-04329

Lantian Li Zhiyuan Tang Dong Wang 0013 Yang Feng 0004 Shiyue Zhang 0001 Collaborative Learning for Language and Speaker Recognition. 2016 abs/1609.08442 CoRR http://arxiv.org/abs/1609.08442 db/journals/corr/corr1609.html#LiTWFZ16

Zhiyuan Tang Ying Shi 0001 Dong Wang 0013 Yang Feng 0004 Shiyue Zhang 0001 Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition. 2016 abs/1609.08789 CoRR http://arxiv.org/abs/1609.08789 db/journals/corr/corr1609.html#TangSWFZ16

Andrew Abel Mijit Ablimit Roee Aharoni Bang An Mohit Bansal Shuyang Cao Arie Cattan Asli Celikyilmaz Vishrav Chaudhary Jennifer L. Chen Pengxiang Cheng 0001 James Cross 0003 Ido Dagan Mark Dredze Yang Feng 0004 Benjamin Frey Jianfeng Gao 0001 Naman Goyal 0001 Francisco Guzmán Askar Hamdulla Peter Hase Yinuo Hu Ozan Irsoy Hyounghun Kim Ayal Klein Sarah Kwan Aodong Li Guanyu Li Lantian Li Steven Lu 0003 Gulnigar Mahmut Anisha Mascarenhas Abigail PanterAbigail T. Panter Duccio Pappadopulo Daniel Preotiuc-Pietro Karthik Radhakrishnan Colin Raffel Paul Roit David S. Rosenberg Swarnadeep Saha Viji Sathy Ying Shi 0001 Idan Szpektor Derek Tam Zhiyuan Tang Zineng Tang David Wan Dong Wang 0013 Lu Wang 0008 Yang Wang Guillaume Wenzek Shijie Wu Harry Xie Pengtao Xie Eric P. Xing Shipeng Xu Hongzhi Yu Andi Zhang 0002 Jiyuan Zhang 0001 Zheling Zhang Thomas Fang Zheng Xiang Zhou