Table of Contents

• Can Language Models Serve as Text-Based World Simulators?Ruoyao Wang, Graham Todd, Ziang Xiao, Xingdi Yuan, Marc-Alexandre Côté, Peter Clark, Peter A. Jansen. 1-17 [doi]
• Feriji: A French-Zarma Parallel Corpus, Glossary & TranslatorMamadou Keita, Elysabhete Amadou Ibrahim, Habibatou Abdoulaye Alfari, Christopher Homan. 1-9 [doi]
• Pragmatic inference of scalar implicature by LLMsYe-eun Cho, Seong mook Kim. 10-20 [doi]
• FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language ModelsAndrew Zhu, Alyssa Hwang, Liam Dugan, Chris Callison-Burch. 18-37 [doi]
• Topic Modeling for Short Texts with Large Language ModelsTomoki Doi, Masaru Isonuma, Hitomi Yanaka. 21-33 [doi]
• Can LLMs substitute SQL? Comparing Resource Utilization of Querying LLMs versus Traditional Relational DatabasesXiang Zhang, Khatoon Khedri, Reza Rawassizadeh. 34-41 [doi]
• Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit DistanceYewei Song, Cedric Lothritz, Xunzhu Tang, Tegawendé F. Bissyandé, Jacques Klein. 38-46 [doi]
• Speech-to-Speech Translation with Discrete-Unit-Based Style TransferYongqi Wang, Jionghao Bai, Rongjie Huang, Ruiqi Li, Zhiqing Hong, Zhou Zhao. 42-49 [doi]
• Resisting the Lure of the Skyline: Grounding Practices in Active Learning for Morphological InflectionSaliha Muradoglu, Michael Ginn, Miikka Silfverberg, Mans Hulden. 47-55 [doi]
• InstructCoder: Instruction Tuning Large Language Models for Code EditingKaixin Li, Qisheng Hu, James Xu Zhao, Hui Chen, Yuxi Xie, Tiedong Liu, Michael Shieh, Junxian He. 50-70 [doi]
• Speculative Contrastive DecodingHongyi Yuan, Keming Lu, Fei Huang 0004, Zheng Yuan 0002, Chang Zhou. 56-64 [doi]
• RDRec: Rationale Distillation for LLM-based RecommendationXinfeng Wang, Jin Cui, Yoshimi Suzuki, Fumiyo Fukumoto. 65-74 [doi]
• BiasDPO: Mitigating Bias in Language Models through Direct Preference OptimizationAhmed Allam. 71-79 [doi]
• Isotropy, Clusters, and ClassifiersTimothee Mickus, Stig-Arne Grönroos, Joseph Attieh. 75-84 [doi]
• MoExtend: Tuning New Experts for Modality and Task ExtensionShanShan Zhong, Shanghua Gao, Zhongzhan Huang, Wushao Wen, Marinka Zitnik, Pan Zhou 0002. 80-91 [doi]
• Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic TasksAndrew Gambardella, Yusuke Iwasawa, Yutaka Matsuo. 85-91 [doi]
• Simpson's Paradox and the Accuracy-Fluency Tradeoff in TranslationZheng Wei Lim, Ekaterina Vylomova, Trevor Cohn, Charles Kemp. 92-103 [doi]
• On the Interpretability of Deep Learning Models for Collaborative Argumentation Analysis in ClassroomsDeLiang Wang, Gaowei Chen. 92-102 [doi]
• Document Alignment based on Overlapping Fixed-Length SegmentsXiaotian Wang, Takehito Utsuro, Masaaki Nagata. 103-113 [doi]
• UltraSparseBERT: 99% Conditionally Sparse Language ModellingPeter Belcak, Roger Wattenhofer. 104-108 [doi]
• SceMQA: A Scientific College Entrance Level Multimodal Question Answering BenchmarkZhenwen Liang, Kehan Guo, Gang Liu, Taicheng Guo, Yujun Zhou 0002, Tianyu Yang, Jiajun Jiao, Renjie Pi, Jipeng Zhang, Xiangliang Zhang 0001. 109-119 [doi]
• Automatically Suggesting Diverse Example Sentences for L2 Japanese Learners Using Pre-Trained Language ModelsEnrico Benedetti, Akiko Aizawa, Florian Boudin. 114-131 [doi]
• On the Role of Long-tail Knowledge in Retrieval Augmented Large Language ModelsDongyang Li, Junbing Yan, Taolin Zhang, Chengyu Wang 0001, Xiaofeng He, Longtao Huang, Hui Xue 0001, Jun Huang 0007. 120-126 [doi]
• IEPile: Unearthing Large Scale Schema-Conditioned Information Extraction CorpusHonghao Gui, Lin Yuan, Hongbin Ye, Ningyu Zhang 0001, Mengshu Sun, Lei Liang, Huajun Chen. 127-146 [doi]
• Z-coref: Thai Coreference and Zero Pronoun ResolutionPoomphob Suwannapichat, Sansiri Tarnpradab, Santitham Prom-on. 132-139 [doi]
• ReMAG-KR: Retrieval and Medically Assisted Generation with Knowledge Reduction for Medical Question AnsweringSidhaarth Murali, Sowmya S., Supreetha R.. 140-145 [doi]
• Plot Retrieval as an Assessment of Abstract Semantic AssociationShicheng Xu, Liang Pang, Jiangnan Li, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou 0016. 146-161 [doi]
• Bi-Directional Multi-Granularity Generation Framework for Knowledge Graph-to-Text with Large Language ModelHaowei Du, Chen Li, Dinghao Zhang, Dongyan Zhao 0001. 147-152 [doi]
• Code-Switching Can be Better Aligners: Advancing Cross-Lingual SLU through Representation-Level and Prediction-Level AlignmentZhihong Zhu, Xuxin Cheng, Zhanpeng Chen, Xianwei Zhuang, Zhiqi Huang, Yuexian Zou. 153-160 [doi]
• AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large ModelsZeyu Liu 0003, Souvik Kundu 0002, Anni Li, Junrui Wan, Lianghao Jiang, Peter A. Beerel. 161-167 [doi]
• Demystifying Instruction Mixing for Fine-tuning Large Language ModelsRenxi Wang, Haonan Li 0002, Minghao Wu, Yuxia Wang, Xudong Han, Chiyu Zhang, Timothy Baldwin. 162-169 [doi]
• DDPrompt: Differential Diversity Prompting in Large Language ModelsLin Mu, Wenhao Zhang, Yiwen Zhang, Peiquan Jin. 168-174 [doi]
• Fine-Tuning ASR models for Very Low-Resource Languages: A Study on MvskokeJulia Mainzinger, Gina-Anne Levow. 170-176 [doi]
• Monotonic Representation of Numeric Attributes in Language ModelsBenjamin Heinzerling, Kentaro Inui. 175-195 [doi]
• Automating Qualitative Data Analysis with Large Language ModelsAngelina Parfenova, Alexander Denzler, Jörgen Pfeffer. 177-185 [doi]
• ANHALTEN: Cross-Lingual Transfer for German Token-Level Reference-Free Hallucination DetectionJanek Herrlein, Chia-Chien Hung, Goran Glavas. 186-194 [doi]
• Label-Aware Automatic Verbalizer for Few-Shot Text Classification in Mid-To-Low Resource LanguagesThanakorn Thaminkaew, Piyawat Lertvittayakumjorn, Peerapon Vateekul. 195-203 [doi]
• Two Issues with Chinese Spelling Correction and A Refinement SolutionChangxuan Sun, Linlin She, Xuesong Lu. 196-204 [doi]
• Vector Spaces for Quantifying Disparity of Multiword Expressions in Annotated TextLouis Estève, Agata Savary, Thomas Lavergne. 204-224 [doi]
• DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph CompletionAnanjan Nandi, Navdeep Kaur, Parag Singla, Mausam. 205-216 [doi]
• Fine-Tuning Pre-Trained Language Models with Gaze SupervisionShuwen Deng, Paul Prasse, David R. Reich, Tobias Scheffer, Lena A. Jäger. 217-224 [doi]
• Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation CampaignsAntonina Sinelnik, Dirk Hovy. 225-237 [doi]
• Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of SpeechAdrien Pupier, Maximin Coavoux, Jérôme Goulian, Benjamin Lecouteux. 225-233 [doi]
• Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit AccessSaibo Geng, Berkay Döner, Chris Wendler, Martin Josifoski, Robert West 0001. 234-245 [doi]
• Assessing In-context Learning and Fine-tuning for Topic Classification of German Web DataJulian Schelb, Andreas Spitz, Roberto Ulloa. 238-252 [doi]
• On the Semantic Latent Space of Diffusion-Based Text-To-Speech ModelsMiri Varshavsky-Hassid, Roy Hirsch, Regev Cohen, Tomer Golany, Daniel Freedman, Ehud Rivlin. 246-255 [doi]
• Knowledge Editing of Large Language Models Unconstrained by Word OrderRyoma Ishigaki, Jundai Suzuki, Masaki Shuzo, Eisaku Maeda. 253-263 [doi]
• Learnable Privacy Neurons Localization in Language ModelsRuizhe Chen, Tianxiang Hu, Yang Feng, Zuozhu Liu. 256-264 [doi]
• Exploring the Effectiveness and Consistency of Task Selection in Intermediate-Task Transfer LearningPin-Jie Lin, Miaoran Zhang, Marius Mosbach, Dietrich Klakow. 264-279 [doi]
• Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMsAkhila Yerukola, Saujas Vaduguru, Daniel Fried, Maarten Sap. 265-275 [doi]
• Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric ParaphrasingShafiuddin Rehan Ahmed, Zhiyong Eric Wang, George Baker, Kevin Stowe, James H. Martin. 276-286 [doi]
• Does the structure of textual content have an impact on language models for automatic summarization?Eve Sauvage, Sabrina Campano, Lydia Ould Ouali, Cyril Grouin. 280-285 [doi]
• Action Inference for Destination Prediction in Vision-and-Language NavigationAnirudh Reddy Kondapally, Kentaro Yamada, Hitomi Yanaka. 286-293 [doi]
• Soft Self-Consistency Improves Language Models AgentsHan Wang, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal. 287-301 [doi]
• A Computational Analysis and Exploration of Linguistic Borrowings in French Rap LyricsLucas Zurbuchen, Rob Voigt. 294-302 [doi]
• RecGPT: Generative Pre-training for Text-based RecommendationHoang Ngo, Dat Quoc Nguyen. 302-313 [doi]
• On Improving Repository-Level Code QA for Large Language ModelsJan Strich, Florian Schneider 0001, Irina Nikishina, Chris Biemann. 303-338 [doi]
• MTP: A Dataset for Multi-Modal Turning Points in Casual ConversationsGia-Bao Ho, Chang Tan, Zahra Darban, Mahsa Salehi, Reza Haffari, Wray L. Buntine. 314-326 [doi]
• What Does Parameter-free Probing Really Uncover?Tommi Buder-Gröndahl. 327-336 [doi]
• ATLAS: Improving Lay Summarisation with Attribute-based ControlZhihao Zhang, Tomas Goldsack, Carolina Scarton, Chenghua Lin. 337-345 [doi]
• Compromesso! Italian Many-Shot Jailbreaks undermine the safety of Large Language ModelsFabio Pernisi, Dirk Hovy, Paul Röttger. 339-345 [doi]
• EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language ModelsMengfei Du, Binhao Wu, Zejun Li, Xuanjing Huang 0001, Zhongyu Wei. 346-355 [doi]
• Foundation Model for Biomedical Graphs: Integrating Knowledge Graphs and Protein Structures to Large Language ModelsYunsoo Kim. 346-355 [doi]
• ViMedAQA: A Vietnamese Medical Abstractive Question-Answering Dataset and Findings of Large Language ModelMinh-Nam Tran, Phu-Vinh Nguyen, Long Nguyen, Dien Dinh. 356-364 [doi]
• Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench BenchmarkNiklas Wretblad, Fredrik Gordh Riseby, Rahul Biswas, Amin Ahmadi, Oskar Holmström. 356-369 [doi]
• Rescue: Ranking LLM Responses with Partial Ordering to Improve Response GenerationYikun Wang, Rui Zheng, Haoming Li 0019, Qi Zhang 0001, Tao Gui, Fei Liu. 365-376 [doi]
• Dwell in the Beginning: How Language Models Embed Long Documents for Dense RetrievalJoão Coelho, Bruno Martins 0001, João Magalhães, Jamie Callan, Chenyan Xiong. 370-377 [doi]
• Basreh or Basra? Geoparsing Historical Locations in the Svoboda DiariesJolie Zhou, Camille Cole, Annie Chen. 377-390 [doi]
• That's Optional: A Contemporary Exploration of "that" Omission in English Subordinate ClausesElla Rabinovich. 378-385 [doi]
• Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?Haozhe An, Christabel Acquaye, Colin Wang, Zongxia Li, Rachel Rudinger. 386-397 [doi]
• Homophone2Vec: Embedding Space Analysis for Empirical Evaluation of Phonological and Semantic SimilaritySophie Wu, Anita Zheng, Joey Chuang. 391-396 [doi]
• Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question DecompositionTyler McDonald, Ali Emami. 397-410 [doi]
• Explainability and Hate Speech: Structured Explanations Make Social Media Moderators FasterAgostina Calabrese, Leonardo Neves, Neil Shah, Maarten W. Bos, Björn Ross, Mirella Lapata, Francesco Barbieri. 398-408 [doi]
• Born Differently Makes a Difference: Counterfactual Study of Bias in Biography Generation from a Data-to-Text PerspectiveBiaoyan Fang, Ritvik Dinesh, Xiang Dai, Sarvnaz Karimi. 409-424 [doi]
• Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and ChallengesVinay Samuel, Houda Aynaou, Arijit Ghosh Chowdhury, Karthik Venkat Ramanan, Aman Chadha. 411-421 [doi]
• Automatic Derivation of Semantic Representations for Thai Serial Verb Constructions: A Grammar-Based ApproachVipasha Bansal. 422-437 [doi]
• Sign Language Translation with Sentence Embedding SupervisionYasser Hamidullah, Josef van Genabith, Cristina España-Bonet. 425-434 [doi]
• STREAM: Simplified Topic Retrieval, Exploration, and Analysis ModuleAnton Thielmann, Arik Reuter, Christoph Weisser, Gillian Kant, Manish Kumar, Benjamin Säfken. 435-444 [doi]
• Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in ThaiParinthapat Pengpun, Can Udomcharoenchaikit, Weerayut Buaphet, Peerat Limkonchotiwat. 438-457 [doi]
• DocFinQA: A Long-Context Financial Reasoning DatasetVarshini Reddy, Rik Koncel-Kedziorski, Viet Dac Lai, Michael Krumdick, Charles Lovering, Chris Tanner. 445-458 [doi]
• Bridging Distribution Gap via Semantic Rewriting with LLMs to Enhance OOD RobustnessManas Madine. 458-468 [doi]
• MaskLID: Code-Switching Language Identification through Iterative MaskingAmir Hossein Kargaran, François Yvon, Hinrich Schütze. 459-469 [doi]
• CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation UnitsYeeun Kang. 469-481 [doi]
• An Empirical Analysis on Large Language Models in Debate EvaluationXinyi Liu, Pinxin Liu, Hangfeng He 0001. 470-487 [doi]
• An Analysis under a Unified Formulation of Learning Algorithms with Output ConstraintsMooho Song, Jay Yoon Lee. 482-498 [doi]
• Fine-Tuned Machine Translation Metrics Struggle in Unseen DomainsVilém Zouhar, Shuoyang Ding, Anna Currey, Tatyana Badeka, Jenyuan Wang, Brian Thompson 0001. 488-500 [doi]
• Beyond Abstracts: A New Dataset, Prompt Design Strategy and Method for Biomedical Synthesis GenerationJames O'Doherty, Cian Nolan, Yufang Hou, Anya Belz. 499-518 [doi]
• IndicIRSuite: Multilingual Dataset and Neural Information Models for Indian LanguagesSaiful Haq, Ashutosh Sharma, Omar Khattab, Niyati Chhaya, Pushpak Bhattacharyya. 501-509 [doi]
• AGR: Reinforced Causal Agent-Guided Self-explaining RationalizationYunxiao Zhao, Zhiqiang Wang 0005, Xiaoli Li 0001, Jiye Liang, Ru Li 0001. 510-518 [doi]
• Shoulders of Giants: A Look at the Degree and Utility of Openness in NLP ResearchSurangika Ranathunga, Nisansa de Silva, Dilith Jayakody, Aloka Fernando. 519-529 [doi]
• Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot ExamplesSoma Sato, Hayato Tsukagoshi, Ryohei Sasano, Koichi Takeda 0003. 519-530 [doi]
• The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language ModelsNoah Y. Siegel, Oana-Maria Camburu, Nicolas Heess, María Pérez-Ortiz 0001. 530-546 [doi]
• Curriculum Learning for Small Code Language ModelsMarwa Naïr, Kamel Mohammed Yamani, Lynda Said L'Hadj, Riyadh Baghdadi. 531-542 [doi]
• Question-Analysis Prompting Improves LLM Performance in Reasoning TasksDharunish Yugeswardeenoo, Kevin Zhu, Sean O'Brien. 543-554 [doi]
• Naming, Describing, and Quantifying Visual Objects in Humans and LLMsAlberto Testoni, Juell Sprott, Sandro Pezzelle. 547-557 [doi]
• An Individualized News Affective Response DatasetTiancheng Hu, Nigel Collier. 555-563 [doi]
• Are LLMs classical or nonmonotonic reasoners? Lessons from genericsAlina Leidinger, Robert van Rooij, Ekaterina Shutova. 558-573 [doi]
• How Well Do Vision Models Encode Diagram Attributes?Haruto Yoshida, Keito Kudo, Yoichi Aoki, Ryota Tanaka, Itsumi Saito, Keisuke Sakaguchi, Kentaro Inui. 564-575 [doi]
• ConstitutionalExperts: Training a Mixture of Principle-based PromptsSavvas Petridis, Ben Wedin, Ann Yuan, James Wexler, Nithum Thain. 574-582 [doi]
• CheckersGPT: Learning World Models through Language ModelingAbhinav Joshi, Vaibhav Sharma, Ashutosh Modi. 576-588 [doi]
• Time Sensitive Knowledge Editing through Efficient FinetuningXiou Ge, Ali Mousavi 0003, Edouard Grave, Armand Joulin, Kun Qian 0002, Benjamin Han, Mostafa Arefiyan, Yunyao Li 0001. 583-593 [doi]
• In-Context Symbolic Regression: Leveraging Large Language Models for Function DiscoveryMatteo Merler, Katsiaryna Haitsiukevich, Nicola Dainese, Pekka Marttinen. 589-606 [doi]
• PRewrite: Prompt Rewriting with Reinforcement LearningWeize Kong, Spurthi Amba Hombaiah, Mingyang Zhang 0001, Qiaozhu Mei, Michael Bendersky. 594-601 [doi]
• Paraphrasing in Affirmative Terms Improves Negation UnderstandingMohammadHossein Rezaei, Eduardo Blanco 0002. 602-615 [doi]
• STEP: Staged Parameter-Efficient Pre-training for Large Language ModelsKazuki Yano, Takumi Ito, Jun Suzuki 0001. 607-614 [doi]
• Exploring Conditional Variational Mechanism to Pinyin Input Method for Addressing One-to-Many Mappings in Low-Resource ScenariosBin Sun, Jianfeng Li, Hao Zhou, Fandong Meng, Kan Li, Jie Zhou. 616-629 [doi]
• Consistency Training by Synthetic Question Generation for Conversational Question AnsweringHamed Hematian Hemati, Hamid Beigy. 630-639 [doi]
• How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?Anushka Singh, Ananya Sai, Raj Dabre, Ratish Puduppully, Anoop Kunchukuttan, Mitesh M. Khapra. 640-649 [doi]
• Zero-Shot Cross-Lingual Reranking with Large Language Models for Low-Resource LanguagesMofetoluwa Adeyemi, Akintunde Oladipo, Ronak Pradeep, Jimmy Lin. 650-656 [doi]
• Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual SpaceGaurav Verma, Minje Choi, Kartik Sharma, Jamelle Watson-Daniels, Sejoon Oh, Srijan Kumar. 657-664 [doi]
• Guidance-Based Prompt Data Augmentation in Specialized Domains for Named Entity RecognitionHyeonseok Kang, Hyein Seo, Jeesu Jung, Sangkeun Jung, Du-Seong Chang, Riwoo Chung. 665-672 [doi]
• Aligning Large Language Models via Fine-grained SupervisionDehong Xu, Liang Qiu, Minseok Kim, Faisal Ladhak, Jaeyoung Do. 673-680 [doi]
• Annotating FrameNet via Structure-Conditioned Language GenerationXinyue Cui, Swabha Swayamdipta. 681-692 [doi]
• DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback MechanismsAndong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai 0001, Yang Xiang, Muyun Yang, Tiejun Zhao, Min Zhang 0005. 693-704 [doi]
• Towards Artwork Explanation in Large-scale Vision Language ModelsKazuki Hayashi, Yusuke Sakai 0010, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe. 705-729 [doi]
• On the Hallucination in Simultaneous Machine TranslationMeizhi Zhong, Kehai Chen, Zhengshan Xue, Lemao Liu, Mingming Yang, Min Zhang 0005. 730-742 [doi]
• Self-Augmented In-Context Learning for Unsupervised Word TranslationYaoyiran Li, Anna Korhonen, Ivan Vulic. 743-753 [doi]
• RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health RecordsRan Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Bowen Jin, May Dongmei Wang, Joyce C. Ho, Carl Yang 0001. 754-765 [doi]