Publications

@inproceedings{yu2026diversity,
  title     = {Diversity Combining for Multi-Path {LLM} Reasoning},
  author    = {Guangsheng Yu and Litianyi Zhang and Qin Wang and Xu Wang and Mingyuan Li and Shaoxiong Ji and Ren Ping Liu and Massimo Piccardi},
  booktitle = {The Fortieth Annual Conference on Neural Information Processing Systems},
  year      = {2026},
  url       = {https://arxiv.org/abs/2609.38829}
}

@article{ibrahim2026model,
  title   = {Model-Based Quality Assessment for Massively Multilingual Parallel Data},
  author  = {Ibrahim, Abdelaziz and Li, Zihao and Tiedemann, J{\"o}rg and Ji, Shaoxiong},
  journal = {arXiv preprint arXiv:2606.00285},
  year    = {2026},
  url     = {https://arxiv.org/abs/2606.00285}
}

@inproceedings{ji-etal-2026-data,
  title     = {{Data-Centric Continual Pre-training} for 500+ Languages: A New Bilingual Translation Corpus and Multilingual Models},
  author    = {Ji, Shaoxiong  and
               Li, Zihao  and
               Paavola, Jaakko  and
               Luo, Hengyu  and
               Tiedemann, J{\"o}rg},
  editor    = {Liakata, Maria  and
               Moreira, Viviane P.  and
               Zhang, Jiajun  and
               Jurgens, David},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},
  month     = jul,
  year      = {2026},
  address   = {San Diego, California, United States},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.findings-acl.937/},
  doi       = {10.18653/v1/2026.findings-acl.937},
  pages     = {18776--18807},
  isbn      = {979-8-89176-395-1}
}

@inproceedings{ji2026mala,
  title     = {{MaLA}: A Corpus and Data Mix for Massive Language Adaptation of Large Language Models},
  author    = {Ji, Shaoxiong and Li, Zihao and Paavola, Jaakko and Lin, Peiqin and Chen, Pinzhen and O'Brien, Dayy{\'a}n and Luo, Hengyu and Sch{\"u}tze, Hinrich and Tiedemann, J{\"o}rg and Haddow, Barry},
  booktitle = {Proceedings of Conference on Language Modeling (COLM)},
  year      = {2026},
  url       = {https://www.olaresearch.org/MaLA/}
}

@inproceedings{kabir2026xcr,
  title     = {{XCR-Bench}: Benchmarking Cross-Cultural Reasoning in {LLMs} via Culture-Specific Items and Hall's Triad},
  author    = {Kabir, Mohsinul and Ahmed, Tasnim and Rahman, Md Mezbaur and Ji, Shaoxiong and Alhuzali, Hassan and Jiang, Yuechen and Huang, Jimin and Ananiadou, Sophia},
  booktitle = {Proceedings of EMNLP},
  year      = {2026},
  url       = {https://arxiv.org/abs/2601.14063}
}

@inproceedings{li2026cross,
  title     = {Frozen Memory Is Not Enough: Rethinking External Memory as Extraction},
  author    = {Li, Mingyuan and Yu, Guangsheng and Wang, Xu and Ji, Shaoxiong},
  booktitle = {The Fortieth Annual Conference on Neural Information Processing Systems},
  year      = {2026},
  url       = {https://arxiv.org/abs/2608.17050}
}

@inproceedings{li-etal-2026-test,
  title     = {Test-Time Scaling of Reasoning Models for Machine Translation},
  author    = {Li, Zihao  and
               Ji, Shaoxiong  and
               Tiedemann, J{\"o}rg},
  editor    = {Demberg, Vera  and
               Inui, Kentaro  and
               Marquez, Llu{\'i}s},
  booktitle = {Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  month     = mar,
  year      = {2026},
  address   = {Rabat, Morocco},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.eacl-long.133/},
  doi       = {10.18653/v1/2026.eacl-long.133},
  pages     = {2902--2917},
  isbn      = {979-8-89176-380-7}
}

@article{li2026memoryathenaadaptiveroutinglatent,
  title         = {MemoryAthena: Adaptive Routing over Latent and Generated Memories},
  author        = {Mingyuan Li and Guangsheng Yu and Juyuan Zhang and Xu Wang and Zhibo Man and Haonan Zhang and Shaoxiong Ji},
  year          = {2026},
  journal       = {arXiv preprint arXiv:2609.25853},
  archiveprefix = {arXiv},
  primaryclass  = {cs.CL},
  url           = {https://arxiv.org/abs/2609.25853}
}

@inproceedings{na-etal-2026-overview,
  title     = {Overview of the {P}sy{D}ef{D}etect Shared Task at {B}io{NLP} 2026: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations},
  author    = {Na, Hongbin  and
               Wang, Zimu  and
               Chen, Zhaoming  and
               Hua, Yining  and
               Gao, Rena  and
               Yang, Kailai  and
               Chen, Ling  and
               Wang, Wei  and
               Ji, Shaoxiong  and
               Torous, John  and
               Ananiadou, Sophia},
  editor    = {Demner-Fushman, Dina  and
               Ananiadou, Sophia  and
               Roberts, Kirk  and
               Tsujii, Junichi},
  booktitle = {{B}io{NLP} 2026},
  month     = jul,
  year      = {2026},
  address   = {San Diego, California},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.bionlp-1.75/},
  doi       = {10.18653/v1/2026.bionlp-1.75},
  pages     = {932--943},
  isbn      = {979-8-89176-434-7}
}

@inproceedings{na-etal-2026-never,
  title     = {You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations},
  author    = {Na, Hongbin  and
               Wang, Zimu  and
               Chen, Zhaoming  and
               Zhou, Peilin  and
               Hua, Yining  and
               Zhou, Grace Ziqi  and
               Zhang, Haiyang  and
               Shen, Tao  and
               Wang, Wei  and
               Torous, John  and
               Ji, Shaoxiong  and
               Chen, Ling},
  editor    = {Liakata, Maria  and
               Moreira, Viviane P.  and
               Zhang, Jiajun  and
               Jurgens, David},
  booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026},
  month     = jul,
  year      = {2026},
  address   = {San Diego, California, United States},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.findings-acl.708/},
  doi       = {10.18653/v1/2026.findings-acl.708},
  pages     = {14428--14448},
  isbn      = {979-8-89176-395-1}
}

@inproceedings{pei2026reasoning,
  title     = {Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?},
  author    = {Pei, Renhao and Liu, Yihong and Pyysalo, Sampo and Sch{\"u}tze, Hinrich and Ji, Shaoxiong},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year      = {2026},
  url       = {https://arxiv.org/abs/2606.03782}
}

@inproceedings{lin2026culturall,
  title     = {{CulturALL}: Benchmarking Multilingual and Multicultural Competence of {LLMs} on Grounded Tasks},
  author    = {Peiqin Lin and Chenyang Lyu and Wenjiang Luo and Haotian Ye and Md Mehrab Hossain and Chunlan Ma and Shaoxiong Ji and Younes Samih and Bo Zeng and Fan Jiang and Yuanbin Cao and Dilda Duisenbek and Adrian Neo Sau Xun and Daria Pozdniakova and Liubou Misevich and Nevena Marinković and Ngoc Gia Linh Nguyen and Thi Khanh Linh Do and Sarakmatak Sophy and Baotian Hu and Guanhua Chen and Gongbo Tang and Alham Fikri Aji and Longyue Wang and Weihua Luo},
  booktitle = {Proceedings of AACL-IJCNLP},
  url       = {https://arxiv.org/abs/2604.19262},
  year      = {2026}
}

@inproceedings{du2026llms,
  title     = {Are {LLMs} Ready to Assist Physicians? {PhysAssistBench} for Interactive Doctor-Patient-{EHR} Assistance},
  author    = {Tianming Du and Peijie Yu and Sihan Shang and Danli Shi and My Linh Nguyen and Shengbo Gao and Guangyuan Li and Yinghong Yu and Yan Jiang and Qianlong Zhao and Behzad Bozorgtabar and Shaoxiong Ji and Jiazhen Pan and Daniel Rueckert and Jiancheng Yang},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2026},
  year      = {2026},
  url       = {https://arxiv.org/abs/2606.18613}
}

@inproceedings{torunoluselamet-etal-2026-parallel,
  title     = {A Parallel Cross-Lingual Benchmark for Multimodal Idiomaticity Understanding},
  author    = {Torunoğlu-Selamet, Dilara and Arslan, Doğukan and Wilkens, Rodrigo and He, Wei and Eryiğit, Doruk and Pickard, Thomas and Pagano, Adriana S. and Villavicencio, Aline and Eryiğit, Gülşen and Abuczki, Ágnes and Cardoso, Aida and Lazarenka, Alesia and Almassova, Dina and Mendes, Amália and Kanellopoulou, Anna and Brosa-Rodriguez, Antoni and Valkovska, Baiba and Wojtowicz, Beata and Pedersen, Bolette and Hidalgo-Ternero, Carlos Manuel and Liebeskind, Chaya and Jokić, Danka and Alves, Diego and Triantafyllidi, Eleni and Velldal, Erik and Philippy, Fred and Oleskeviciene, Giedre Valunaite and Rizgeliene, Ieva and Skadina, Inguna and Lobzhanidze, Irina and Haugen, Isabell Stinessen and Krito, Jauza Akbar and Marković, Jelena M. and Monti, Johanna and Sauca, Josue Alejandro and Dobrovoljc, Kaja and Ugwuanyi, Kingsley O. and Rituma, Laura and Øvrelid, Lilja and Agro, Maha Tufail and Abjalova, Manzura and Chatzigrigoriou, Maria and Ramos, María del Mar Sánchez and Pendevska, Marija and Seyyedrezaei, Masoumeh and Shamsfard, Mehrnoush and Ahsan, Momina and Khan, Muhammad Ahsan Riaz and Norman, Nathalie Carmen Hau and Ayyıldız, Nilay Erdem and Hosseini-Kivanani, Nina and Ligeti-Nagy, Noémi and Naeem, Numaan and Kanishcheva, Olha and Yatsyshyna, Olha and Orel, Daniil and Giommarelli, Petra and Osenova, Petya and Garabik, Radovan and Semou, Regina E. and Rebechi, Rozane and Pranida, Salsabila Zahirah and Touileb, Samia and Nimb, Sanni and Ahmad, Sarfraz and Sharipova, Sarvinoz and Golan, Shahar and Ji, Shaoxiong and Aboh, Sopuruchi Christian and Sucur, Srdjan and Markantonatou, Stella and Olsen, Sussi and Tajalli, Vahide and Lipp, Veronika and Giouli, Voula and Eraydın, Yelda Yeşildal and Saaberi, Zahra and Xie, Zhuohan},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)},
  month     = {May},
  year      = {2026},
  pages     = {9434--9448},
  address   = {Palma, Mallorca, Spain},
  publisher = {European Language Resources Association (ELRA)},
  editor    = {Piperidis, Stelios and Bel, Núria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio},
  doi       = {10.63317/5cvnbcoktfo2},
  abstract  = {Potentially idiomatic expressions (PIEs) carry meanings inherently tied to the everyday experience of a given language community. As such, they constitute an interesting challenge for assessing the linguistic (and to some extent cultural) capabilities of NLP systems. In this paper, we present XMPIE, a parallel multilingual and multimodal dataset of potentially idiomatic expressions. The dataset, containing 34 languages and over ten thousand items, allows comparative analyses of idiomatic patterns among language-specific realisations and preferences in order to gather insights about shared cultural aspects. This parallel dataset allows evaluation of language model performance for a given PIE in different languages and whether idiomatic understanding in one language can be transferred to another. Moreover, the dataset supports the study of PIEs across textual and visual modalities, to measure to what extent PIE understanding in one modality transfers or implies in understanding in another modality (text vs. image). The data was created by language experts, with both textual and visual components crafted under multilingual guidelines, and each PIE is accompanied by five images representing a spectrum from idiomatic to literal meanings, including semantically related and random distractors. The result is a high-quality benchmark for evaluating multilingual and multimodal idiomatic language understanding.},
  url       = {https://arxiv.org/abs/2601.08645}
}

@article{vakada2026labelfree,
  title   = {Label-Free Steering: Compressing Test-Time Reinforcement Learning into Bias-Only Subspaces},
  author  = {Vakada, Naveen and Li, Mingyuan and Ji, Shaoxiong},
  journal = {arXiv preprint arXiv:2609.18587},
  year    = {2026},
  url     = {https://arxiv.org/abs/2609.18587}
}

@article{zouhar2026translationbenchmark,
  title   = {Last Translation Benchmark},
  author  = {Vilém Zouhar and Niyati Bafna and Mukund Choudhary and Maike Züfle and Sara Rajaee and Pinzhen Chen and Jannis Vamvas and Sara Papi and Ona de Gibert and Bhavitvya Malik and Eliya Habba and Orfeas Menis Mastromichalakis and Patrícia Schmidtová and Michelle Wastl and Sheriff Issaka and Leshem Choshen and Stella Biderman and Antonis Anastasopoulos and Jan Niehues and Rico Sennrich and Mrinmaya Sachan and Ondřej Bojar and Kenton Murray and Jörg Tiedemann and Alham Fikri Aji and Philipp Koehn and Christof Monz and Alexandra Birch and Sowmya Vajjala and Chalamalasetti Kranti and Cristina España-Bonet and Nobin Sarwar and David Kaczér and Shunta Asano and Malik Marmonier and Daban Q. Jaff and Vaisakhi Mishra and Hend Al- Khalifa and Gabriele Sarti and Sourajit Saha and Nils Rehlinger and Juan Daniel Cuervo Villa and Jonathan Tonglet and Saugata Purkayastha and Dominik Macháček and Jagannathan Ramanujam and Heejin Do and Zuzana Nadova and Fred Philippy and Fabian Retkowski and Maria Lymperaiou and Silvia Casola and Hanna Yukhymenko and Shubhashis Roy Dipta and Sangwon Ryu and Andrés Jerez and Ron Keinan and Shuaib Shuaib Yusuf and Avantica Vempati and Maria Carmen Staiano and Sukannya Purkayastha and Adrian Cosma and Vitalii Babenko and Erivan Inan and Aviral Nigam and Wafa Aissa and Fatima Haouari and Venkata Prasanth Kumar Gummadi and Mehdi Jafarzadeh and Valentin Scourneau and Lukas Edman and Kaiser Sun and Shaomu Tan and Mohammad Sadegh Gholizadeh and Johannes-Rudolf David and Dipankar Srirag and Javier García Gilabert and Ruta Binkyte and Manar Ali and Ana-Maria Bucur and Sabry E. Farrag and Youssef Saber and Yihong Liu and Jean Maillard and Cojocaru Nicoleta and Xiaochuang Yuan and Sina Ahmadi and Philipp Mondorf and Kaustubh Dhole and Roman Wixinger and Shenbin Qian and Manuel Tuor and Sergey Troshin and Jonathan Yahav and Fida Mohammad Thoker and Amir Arsalan Rezapour and Lance Calvin Lim Gamboa and Manon Reusens and Kätriin Kukk and Koel Dutta Chowdhury and Giuseppe Gallipoli and Christian Hoang and Shaswati Saha and Seth Aycock and Jan Kocoń and Bo Chen and Linh Vu and Vatsal Venkatkrishna and Arafat Ahsan and Luan Thanh Nguyen and Hassan Soliman and Daryna Dementieva and Theresia Veronika Rampisela and Ngoc Quynh Tram Do and Marius Huber and Kazuki Egashira and Azmine Toushik Wasi and Vladislav Poritski and Mike Zhang and Deep Shah and Paul Gavrikov and Luis Frentzen Salim and David Africa and R. Damanhuri and Bello Umar Bello and Anumit Garg and Gengyu Rao and Pawan Sasanka Ammanamanchi and Kamile Dementaviciute and Andrianos Michail and L D M S Sai Teja and Dawei Zhu and Yi Fan and Wei Liu and Farhan Farsi and Elias Herranen and Sankalan Pal Chowdhury and Karen Sanchez and Farzad Shami and Ashok Urlana and Zimu Wang and Tomasz Limisiewicz and Priyaranjan Pattnayak and Marii Ojastu and Hongbin Na and Emilian Radoi and Chenyi Zhao and Carlos Hinojosa and Andrea Gregor de Varda and Zaid Alyafeai and Reem Alzahrani and Nehal Kathrotia and Alex Flückiger and Ulysses Sekai Tully Carr and Jimson Paulo Layacan and Guy Kaplan and Ritwik Tiwari and Rishit Dagli and Oksana Volchek and Isaac R Caswell and Bowen Yi and Blanka Kövér and Amir Hossein Yari and Aicha Chorana and Zhengxiang Wang and Selja Keränen and Samuel Simko and Joy Olusanya and Jenny Chim and Enzo Doyen and Vivek Harsha Lakkamaneni and Sophia Conrad and Pouya Sadeghi and Panayiotis Panayiotou and Luis Lara and Jannatul Nayem and Eran Yahav and Debanshu Das and Antonia Karamolegkou and Anmol Goel and Aishik Mandal and Tommaso Cerruti and Raoyuan Zhao and Mykola Haltiuk and Thura Aung and Naser Almousa and Amir Hossein Kargaran and Rachel Bawden and Qiaoyuan Zheng and Mateusz Lango and Beni Egressy and Fidel Rodríguez Velásquez and Natchapon Jongwiriyanurak and Minh Ngoc Do and Marco Gaido and Lena Libon and Dzmitry Kuzmin and Badal Nyalang and Antoine Taroni and Andrei Niculae and Abdulaziz Nura Kani and Rushikesh Zawar and Marek Šuppa and Beatrice Savoldi and Andreas Simons and Rayyan Merchant and Ilai Yaron Levy and Francesco Pinto and Ziyi Yang and Yolanda Xavier and Samuel Frontull and Muhammad Ravi Shulthan Habibi and Kenneth Enevoldsen and Harris Abdul Majid and Francesca Padovani and Tim Graf and Tatiana Bielakova and Sharifa Djurabaeva and Shaoxiong Ji and Raia Abu Ahmad and Pavel Stepachev and Jirui Qi and Ayush Sunil Munot and Alireza Pakniat and Ayla Rigouts Terryn and Yuxing Lu and Yurii Paniv and Xiyan Fu and Tosin Adewumi and Sunisth Kumar and Stéphane J. P. S. Thunus and Shree Harsha Bokkahalli Satish and Shayan Bali and Prakhar Gupta and Papa Abdou Karim Karou Diallo and Matija Akrap and Marko Culjak and Kristýna Onderková and Joseph Attieh and Esrael Teferi Tensay and Elisabeth Fittschen and Benoît Sagot and Jingwei Ni and Yu Fan},
  year    = {2026},
  journal = {arXiv preprint arXiv:2609.04173},
  url     = {https://arxiv.org/abs/2609.04173}
}

@article{vyalla2026psychologically,
  title   = {Psychologically-Grounded Graph Modeling for Interpretable Depression Detection},
  author  = {Vyalla, Rishitej Reddy and Prasad, Kritarth and Anand, Avinash and Cambria, Erik and Ji, Shaoxiong and Alamri, Faten S and Wang, Zhengkui},
  journal = {arXiv preprint arXiv:2604.24126},
  year    = {2026},
  url     = {https://arxiv.org/abs/2604.24126}
}

@article{tu2026trainingspecialistmodelsreasoning,
  title   = {Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation},
  author  = {Yilei Tu and Zihao Li and Shaoxiong Ji and Jörg Tiedemann and Fei Yuan},
  year    = {2026},
  journal = {arXiv preprint arXiv:2609.13770},
  url     = {https://arxiv.org/abs/2609.13770}
}

@article{yu2025graph2text,
  author     = {Yu, Shuo and Wang, Yingbo and Li, Ruolin and Liu, Guchun and Shen, Yanming and Ji, Shaoxiong and Li, Bowen and Han, Fengling and Zhang, Xiuzhen and Xia, Feng},
  title      = {Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning},
  year       = {2026},
  issue_date = {March 2026},
  publisher  = {Association for Computing Machinery},
  address    = {New York, NY, USA},
  volume     = {44},
  number     = {3},
  issn       = {1046-8188},
  url        = {https://doi.org/10.1145/3786600},
  doi        = {10.1145/3786600},
  abstract   = {Graphs are prevalent in numerous real-world applications. Previous methods directly model graph structures and achieve significant success. However, these methods encounter bottlenecks due to the inherent irregularity of graphs. An innovative solution is converting graphs into textual representations, thereby harnessing the powerful capabilities of Large Language Models (LLMs) to process and comprehend graphs. In this article, we present a comprehensive review of methodologies for applying LLMs to graphs, termed LLM4graph. The core of LLM4graph lies in transforming graphs into texts for LLMs to understand and analyze. Thus, we propose a novel taxonomy of LLM4graph methods from the view of the transformation. Specifically, existing methods can be divided into two paradigms: Graph2text and Graph2token, which transform graphs into texts or tokens as the input of LLMs, respectively. We point out four challenges during the transformation to systematically present existing methods from a problem-oriented perspective. For practical concerns, we provide a guideline for researchers on selecting appropriate models and LLMs for different graphs and hardware constraints. To empirically evaluate our taxonomy and different technical choices, we conduct experiments with representative methods in Graph2text and Graph2token. We also identify five future research directions for LLM4graph.},
  journal    = {ACM Trans. Inf. Syst.},
  month      = feb,
  articleno  = {57},
  numpages   = {49},
  keywords   = {Graph data, Large language model, Graph to text, Graph to token, Graph learning}
}

@inproceedings{vu2025roleplaying,
  title     = {Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires},
  author    = {Doan Nam Long Vu and Rui Tan and Lena Moench and Svenja Jule Francke and Daniel Woiwod and Florian Thomas-Odenthal and Sanna Stroth and Tilo Kircher and Christiane Hermann and Udo Dannlowski and Hamidreza Jamalabadi and Simone Balloccu and Shaoxiong Ji},
  booktitle = {Proceedings of the Fifth Workshop on NLP for Positive Impact},
  year      = {2025},
  url       = {https://arxiv.org/abs/2510.25384}
}

@inproceedings{li2025rethinking,
  title     = {Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting {LLMs} Across Languages and Resources},
  author    = {Li, Zihao and Ji, Shaoxiong and Luo, Hengyu and Tiedemann, J{\"o}rg},
  booktitle = {Conference on Language Modeling ({COLM})},
  year      = {2025},
  url       = {https://openreview.net/pdf?id=mpTIzK4Zca}
}

@inproceedings{luo2025gloteval,
  title     = {{G}lot{E}val: A Test Suite for Massively Multilingual Evaluation of Large Language Models},
  author    = {Luo, Hengyu and Li, Zihao and Attieh, Joseph and Devkota, Sawal and de Gibert, Ona and Huang, Xu and Ji, Shaoxiong and Lin, Peiqin and Mantina, Bhavani Sai Praneeth Varma and Sreenidhi, Ananda and V{\'a}zquez, Ra{\'u}l and Wang, Mengjie and Yusofi, Samea and Yuan, Fei and Tiedemann, J{\"o}rg},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations},
  pages     = {602--614},
  year      = {2025},
  doi       = {10.18653/v1/2025.emnlp-demos.43},
  url       = {https://aclanthology.org/2025.emnlp-demos.43/}
}