MoCo: A One-Stop Shop for Model Collaboration Research.

Wenxuan Ding 0001 HKUST, Hong Kong, SAR, China Wenxuan Ding Wenxuan Ding 0002 University of Illinois, Chicago, IL, USA Wenxuan Ding 0003 University of Texas at Austin, Department of Computer Science, TX, USA Wenxuan Ding 0004 New York University, NY, USA

Shangbin Feng Yuyang Bai Ziyuan Yang Yike Wang 0002 Zhaoxuan Tan Jiajie Yan Zhen Lei 0001 Wenxuan Ding 0001 Weijia Shi Haojin Wang Zhenting Qi Yuru Jiang Heng Wang 0008 Chengsong Huang Yu Fei Jihan Yao Yilun Du Luke Zettlemoyer Yejin Choi 0001 Yulia Tsvetkov MoCo: A One-Stop Shop for Model Collaboration Research. 2026 January abs/2601.21257 CoRR https://doi.org/10.48550/arXiv.2601.21257 db/journals/corr/corr2601.html#abs-2601-21257 streams/journals/corr

Ziyuan Yang Wenxuan Ding 0001 Shangbin Feng Yulia Tsvetkov Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems. 2026 February abs/2602.05176 CoRR https://doi.org/10.48550/arXiv.2602.05176 db/journals/corr/corr2602.html#abs-2602-05176 streams/journals/corr

Wenxuan Ding 0001 Nicholas Tomlin Greg Durrett Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents. 2026 February abs/2602.16699 CoRR https://doi.org/10.48550/arXiv.2602.16699 db/journals/corr/corr2602.html#abs-2602-16699 streams/journals/corr

Weiqi Wang 0001 Tianqing Fang Haochen Shi Baixuan Xu Wenxuan Ding 0001 Liyu Zhang 0005 Wei Fan 0001 Jiaxin Bai Haoran Li 0003 Xin Liu 0039 Yangqiu Song On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions. EMNLP (Findings) 2025 2260-2281 conf/emnlp/2025f https://aclanthology.org/2025.findings-emnlp.122/ db/conf/emnlp/emnlp2025f.html#WangFSXDZFBLLS25 streams/conf/emnlp Jihan Yao Wenxuan Ding 0001 Shangbin Feng Lucy Lu Wang Yulia Tsvetkov Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only. 2025 ICLR https://openreview.net/forum?id=p74CpDzw1Y conf/iclr/2025 db/conf/iclr/iclr2025.html#Yao0FWT25

Shangbin Feng Wenxuan Ding 0001 Alisa Liu Zifeng Wang 0002 Weijia Shi Yike Wang 0002 Zejiang Shen 0001 Xiaochuang Han Hunter Lang Chen-Yu Lee Tomas Pfister Yejin Choi 0001 Yulia Tsvetkov When One LLM Drools, Multi-LLM Collaboration Rules. 2025 February abs/2502.04506 CoRR https://doi.org/10.48550/arXiv.2502.04506 db/journals/corr/corr2502.html#abs-2502-04506 streams/journals/corr

Yuru Jiang Wenxuan Ding 0001 Shangbin Feng Greg Durrett Yulia Tsvetkov SPARTA ALIGNMENT: Collectively Aligning Multiple Language Models through Combat. 2025 June abs/2506.04721 CoRR https://doi.org/10.48550/arXiv.2506.04721 db/journals/corr/corr2506.html#abs-2506-04721 streams/journals/corr

Weiqi Wang 0001 Tianqing Fang Chunyang Li Haochen Shi Wenxuan Ding 0001 Baixuan Xu Zhaowei Wang 0003 Jiaxin Bai Xin Liu 0039 Cheng Jiayang Chunkit Chan Yangqiu Song CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning. 2351-2374 2024 ACL (1) https://doi.org/10.18653/v1/2024.acl-long.128 https://aclanthology.org/2024.acl-long.128 https://www.wikidata.org/entity/Q131457745 conf/acl/2024-1 db/conf/acl/acl2024-1.html#0001FLS0XWBLJCS24 Wenxuan Ding 0001 Shangbin Feng Yuhan Liu Zhaoxuan Tan Vidhisha Balachandran Tianxing He Yulia Tsvetkov Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models. 2609-2636 2024 ACL (Findings) https://doi.org/10.18653/v1/2024.findings-acl.154 https://aclanthology.org/2024.findings-acl.154 conf/acl/2024f db/conf/acl/acl2024f.html#0001FLTBHT24 Shangbin Feng Weijia Shi Yike Wang 0002 Wenxuan Ding 0001 Vidhisha Balachandran Yulia Tsvetkov Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration. 14664-14690 2024 ACL (1) https://doi.org/10.18653/v1/2024.acl-long.786 https://aclanthology.org/2024.acl-long.786 conf/acl/2024-1 db/conf/acl/acl2024-1.html#FengS00BT24 Wenxuan Ding 0001 Weiqi Wang 0001 Sze Heng Douglas Kwok Minghao Liu Tianqing Fang Jiaxin Bai Xin Liu 0039 Changlong Yu Zheng Li 0018 Chen Luo 0003 Qingyu Yin Bing Yin Junxian He Yangqiu Song IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce. 2247-2266 2024 EMNLP (Findings) https://doi.org/10.18653/v1/2024.findings-emnlp.123 https://aclanthology.org/2024.findings-emnlp.123 conf/emnlp/2024f db/conf/emnlp/emnlp2024f.html#0001WKLFBLYLLYY24 Shangbin Feng Weijia Shi Yike Wang 0002 Wenxuan Ding 0001 Orevaoghene Ahia Shuyue Stella Li Vidhisha Balachandran Sunayana Sitaram Yulia Tsvetkov Teaching LLMs to Abstain across Languages via Multilingual Feedback. 4125-4150 2024 EMNLP https://doi.org/10.18653/v1/2024.emnlp-main.239 https://aclanthology.org/2024.emnlp-main.239 conf/emnlp/2024 db/conf/emnlp/emnlp2024.html#FengS00ALBST24 Baixuan Xu Weiqi Wang 0001 Haochen Shi Wenxuan Ding 0001 Huihao Jing Tianqing Fang Jiaxin Bai Xin Liu 0039 Changlong Yu Zheng Li 0018 Chen Luo 0003 Qingyu Yin Bing Yin Long Chen 0016 Yangqiu Song MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding. 7800-7815 2024 EMNLP https://doi.org/10.18653/v1/2024.emnlp-main.446 https://aclanthology.org/2024.emnlp-main.446 conf/emnlp/2024 db/conf/emnlp/emnlp2024.html#Xu0S0JFBLYLLYYC24

Weiqi Wang 0001 Tianqing Fang Chunyang Li Haochen Shi Wenxuan Ding 0001 Baixuan Xu Zhaowei Wang 0003 Jiaxin Bai Xin Liu 0039 Jiayang Cheng Chunkit Chan Yangqiu Song CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning. 2024 abs/2401.07286 CoRR https://doi.org/10.48550/arXiv.2401.07286 db/journals/corr/corr2401.html#abs-2401-07286

Shangbin Feng Weijia Shi Yike Wang 0002 Wenxuan Ding 0001 Vidhisha Balachandran Yulia Tsvetkov Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration. 2024 abs/2402.00367 CoRR https://doi.org/10.48550/arXiv.2402.00367 db/journals/corr/corr2402.html#abs-2402-00367

Wenxuan Ding 0001 Weiqi Wang 0001 Sze Heng Douglas Kwok Minghao Liu Tianqing Fang Jiaxin Bai Junxian He Yangqiu Song IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce. 2024 abs/2406.10173 CoRR https://doi.org/10.48550/arXiv.2406.10173 db/journals/corr/corr2406.html#abs-2406-10173

Baixuan Xu Weiqi Wang 0001 Haochen Shi Wenxuan Ding 0001 Huihao Jing Tianqing Fang Jiaxin Bai Xin Liu 0039 Changlong Yu Zheng Li 0018 Chen Luo 0003 Qingyu Yin Bing Yin Long Chen 0016 Yangqiu Song MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding. 2024 abs/2406.10701 CoRR https://doi.org/10.48550/arXiv.2406.10701 db/journals/corr/corr2406.html#abs-2406-10701 streams/journals/corr

Shangbin Feng Weijia Shi Yike Wang 0002 Wenxuan Ding 0001 Orevaoghene Ahia Shuyue Stella Li Vidhisha Balachandran Sunayana Sitaram Yulia Tsvetkov Teaching LLMs to Abstain across Languages via Multilingual Feedback. 2024 abs/2406.15948 CoRR https://doi.org/10.48550/arXiv.2406.15948 db/journals/corr/corr2406.html#abs-2406-15948

Jihan Yao Wenxuan Ding 0001 Shangbin Feng Lucy Lu Wang Yulia Tsvetkov Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only. 2024 abs/2410.11055 CoRR https://doi.org/10.48550/arXiv.2410.11055 db/journals/corr/corr2410.html#abs-2410-11055 streams/journals/corr

Weiqi Wang 0001 Tianqing Fang Wenxuan Ding 0001 Baixuan Xu Xin Liu 0039 Yangqiu Song Antoine Bosselut CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering. 13520-13545 2023 EMNLP (Findings) https://doi.org/10.18653/v1/2023.findings-emnlp.902 https://aclanthology.org/2023.findings-emnlp.902 conf/emnlp/2023f db/conf/emnlp/emnlp2023f.html#WangF0XLSB23 Haochen Shi Weiqi Wang 0001 Tianqing Fang Baixuan Xu Wenxuan Ding 0001 Xin Liu 0039 Yangqiu Song QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering. 15329-15341 2023 EMNLP (Findings) https://doi.org/10.18653/v1/2023.findings-emnlp.1023 https://aclanthology.org/2023.findings-emnlp.1023 conf/emnlp/2023f db/conf/emnlp/emnlp2023f.html#ShiWFX0LS23

Weiqi Wang 0001 Tianqing Fang Wenxuan Ding 0001 Baixuan Xu Xin Liu 0039 Yangqiu Song Antoine Bosselut CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering. 2023 abs/2305.14869 CoRR https://doi.org/10.48550/arXiv.2305.14869 db/journals/corr/corr2305.html#abs-2305-14869

Wenxuan Ding 0001 Shangbin Feng Yuhan Liu Zhaoxuan Tan Vidhisha Balachandran Tianxing He Yulia Tsvetkov Knowledge Crosswords: Geometric Reasoning over Structured Knowledge with Large Language Models. 2023 abs/2310.01290 CoRR https://doi.org/10.48550/arXiv.2310.01290 db/journals/corr/corr2310.html#abs-2310-01290

Haochen Shi Weiqi Wang 0001 Tianqing Fang Baixuan Xu Wenxuan Ding 0001 Xin Liu 0039 Yangqiu Song QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering. 2023 abs/2310.11303 CoRR https://doi.org/10.48550/arXiv.2310.11303 db/journals/corr/corr2310.html#abs-2310-11303

Orevaoghene Ahia Jiaxin Bai Yuyang Bai Vidhisha Balachandran Antoine Bosselut Chunkit Chan Long Chen 0016 Yejin Choi 0001 Yilun Du Greg Durrett Wei Fan 0001 Tianqing Fang Yu Fei Shangbin Feng Xiaochuang Han Junxian He Tianxing He Chengsong Huang Yuru Jiang Cheng JiayangJiayang Cheng Huihao Jing Sze Heng Douglas Kwok Hunter Lang Chen-Yu Lee Zhen Lei 0001 Chunyang Li Haoran Li 0003 Shuyue Stella Li Zheng Li 0018 Alisa Liu Minghao Liu Xin Liu 0039 Yuhan Liu Chen Luo 0003 Tomas Pfister Zhenting Qi Shannon Shen 0001Zejiang Shen 0001 Haochen Shi Weijia Shi Sunayana Sitaram Yangqiu Song Zhaoxuan Tan Nicholas Tomlin Yulia Tsvetkov Haojin Wang Heng Wang 0008 Lucy Lu Wang Weiqi Wang 0001 Yike Wang 0002 Zhaowei Wang 0003 Zifeng Wang 0002 Baixuan Xu Jiajie Yan Ziyuan Yang Jihan Yao Bing Yin Qingyu Yin Changlong Yu Luke Zettlemoyer Liyu Zhang 0005