Table of Contents

• Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM LeaderboardChanjun Park, Hyeonwoo Kim. 1-8 [doi]
• RTSM: Knowledge Distillation with Diverse Signals for Efficient Real-Time Semantic Matching in E-CommerceSanjay Agrawal 0006, Vivek Sembium. 9-19 [doi]
• WorkTeam: Constructing Workflows from Natural Language with Multi-AgentsHanchao Liu, Rongjun Li, Weimin Xiong, Ziyu Zhou, Wei Peng 0011. 20-35 [doi]
• How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark DatasetQiang Li, Mingkun Tan, Xun Zhao, Dan Zhang, Daoan Zhang, Shengzhao Lei, Anderson S. Chu, Lujun Li, Porawit Kamnoedboon. 36-53 [doi]
• Text2Sql: Pure Fine-Tuning and Pure Knowledge DistillationGao yu Zhu, Wei Shao, Xichou Zhu, Lei Yu 0012, Jiafeng Guo, Xueqi Cheng. 54-61 [doi]
• MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal AnsweringVinay Kumar Verma, Shreyas Sunil Kulkarni, Happy Mittal, Deepak Gupta. 62-69 [doi]
• Finding-Centric Structuring of Japanese Radiology Reports and Analysis of Performance Gaps for Multiple FacilitiesYuki Tagawa, Yohei Momoki, Norihisa Nakano, Ryota Ozaki, Motoki Taniguchi, Masatoshi Hori, Noriyuki Tomiyama. 70-85 [doi]
• Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level UnderstandingsXuanqing Liu, Luyang Kong, Wei Niu, Afshin Khashei, Belinda Zeng, Steve Johnson, Jon Jay, Davor Golac, Matt Pope. 86-98 [doi]
• Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual TranslationYi-Chang Chen, Po-Chun Hsu, Chan-Jan Hsu, Da-shan Shiu. 99-111 [doi]
• Exploring Straightforward Methods for Automatic Conversational Red-TeamingGeorge Kour, Naama Zwerdling, Marcel Zalmanovici, Ateret Anaby-Tavor, Ora Nova Fandina, Eitan Farchi. 112-128 [doi]
• A Diverse and Effective Retrieval-Based Debt Collection System with Expert KnowledgeJiaming Luo, Weiyi Luo, Guoqing Sun, Mengchen Zhu, Haifeng Tang, Kenny Q. Zhu, Mengyue Wu. 129-137 [doi]
• Search Query Embeddings via User-behavior-driven Contrastive LearningSosuke Nishikawa, Jun Hirako, Nobuhiro Kaji, Koki Watanabe, Hiroki Asano, Souta Yamashiro, Shumpei Sano. 138-147 [doi]
• QSpell 250K: A Large-Scale, Practical Dataset for Chinese Search Query Spell CorrectionDezhi Ye, Haomei Jia, Junwei Hu, Bowen Tian, Jie Liu, Haijin Liang, Jin Ma 0003, Wenmin Wang 0001. 148-155 [doi]
• CONSTRUCTA: Automating Commercial Construction Schedules in Fabrication Facilities with Large Language ModelsYifan Zhang, Xue Yang. 156-172 [doi]
• Challenges and Remedies of Domain-Specific Classifiers as LLM Guardrails: Self-Harm as a Case StudyBing Zhang, Guang-Jie Ren. 173-182 [doi]
• Mitigating Bias in Item Retrieval for Enhancing Exam Assembly in Vocational Education ServicesAlonso Palomino, Andreas Fischer, David Buschhüter, Roland Roller, Niels Pinkwart, Benjamin Paassen. 183-193 [doi]
• Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic PerformanceSomnath Banerjee 0002, Avik Halder, Rajarshi Mandal, Sayan Layek, Ian Soboroff, Rima Hazra, Animesh Mukherjee 0001. 194-209 [doi]
• Towards Reliable and Practical Phishing DetectionHyowon Cho, Minjoon Seo. 210-225 [doi]
• Zero-Shot ATC Coding with Large Language Models for Clinical AssessmentsZijian Chen, John-Michael Gamble, Jimmy Lin. 226-232 [doi]
• Navigating the Path of Writing: Outline-guided Text Generation with Large Language ModelsYukyung Lee, Soonwon Ka, Bokyung Son, Pilsung Kang 0001, Jaewook Kang. 233-250 [doi]
• TaeBench: Improving Quality of Toxic Adversarial ExamplesJennifer Zhu, Dmitriy Bespalov, Liwen You, Ninad Kulkarni, Yanjun Qi. 251-265 [doi]
• Open Ko-LLM Leaderboard2: Bridging Foundational and Practical Evaluation for Korean LLMsHyeonwoo Kim, Dahyun Kim 0001, Jihoo Kim, Sukyung Lee, Yungi Kim, Chanjun Park. 266-273 [doi]
• CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph ReasoningZukang Yang, Zixuan Zhu, Jennifer Zhu. 274-286 [doi]
• CharacterGPT: A Persona Reconstruction Framework for Role-Playing AgentsJeiyoon Park, Chanjun Park, HeuiSeok Lim. 287-303 [doi]
• Efficient Continual Pre-training of LLMs for Low-resource LanguagesArijit Nag, Soumen Chakrabarti, Animesh Mukherjee 0001, Niloy Ganguly. 304-317 [doi]
• DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent DetectionPei Guo, Enjie Liu, Ruichao Zhong, Mochi Gao, Yunzhi Tan, Bo Hu, Zang Li. 318-328 [doi]
• Octopus: On-device language model for function calling of software APIsWei Chen, Zhiyuan Li, Mingyuan Ma. 329-339 [doi]
• MoFE: Mixture of Frozen Experts ArchitectureJean Seo, Jaeyoon Kim, Hyopil Shin. 340-348 [doi]
• FinLLM-B: When Large Language Models Meet Financial Breakout TradingKang Zhang, Osamu Yoshie, Lichao Sun, Weiran Huang 0001. 349-357 [doi]
• QueryShield: A Platform to Mitigate Enterprise Data Leakage in Queries to External LLMsNitin Ramrakhiyani, Delton Myalil, Sachin Pawar, Manoj Apte, Rajan Ma, Divyesh Saglani, Imtiyazuddin Shaik. 358-369 [doi]
• SwissADT: An Audio Description Translation System for Swiss LanguagesLukas Fischer 0003, Yingqiang Gao, Alexa Lintner, Annette Rios, Sarah Ebling. 370-379 [doi]
• Chinese Morph Resolution in E-commerce Live Streaming ScenariosJiahao Zhu, Jipeng Qiang, Ran Bai, Chenyu Liu, Xiaoye Ouyang. 380-389 [doi]
• MonoTODia: Translating Monologue Requests to Task-Oriented DialoguesSebastian Steindl, Ulrich Schäfer 0001, Bernd Ludwig. 390-403 [doi]
• MedEthicEval: Evaluating Large Language Models Based on Chinese Medical EthicsHaoan Jin, Jiacheng Shi, Hanhui Xu, Kenny Q. Zhu, Mengyue Wu. 404-421 [doi]
• Predicting ICU Length of Stay for Patients using Latent Categorization of Health ConditionsTirthankar Dasgupta, Manjira Sinha, Sudeshna Jana. 422-430 [doi]
• RevieWeaver: Weaving Together Review Insights by Leveraging LLMs and Semantic SimilarityJiban Adhikary, Mohammad Alqudah 0004, Arun Palghat Udayashankar. 431-448 [doi]
• MedCodER: A Generative AI Assistant for Medical CodingKrishanu Das Baksi, Elijah Soba, John J. Higgins, Ravi Saini, Jaden Wood, Jane Cook, Jack Scott, Nirmala Pudota, Tim Weninger, Edward Bowen, Sanmitra Bhattacharya. 449-459 [doi]
• Visual Zero-Shot E-Commerce Product Attribute Value ExtractionJiaying Gong, Ming Cheng, Hongda Shen, Pierre-Yves Vandenbussche, Janet Jenq, Hoda Eldardiry. 460-469 [doi]
• SCORE: Systematic COnsistency and Robustness Evaluation for Large Language ModelsGrigor Nalbandyan, Rima Shahbazyan, Evelina Bakhturina. 470-484 [doi]
• Evaluating Large Language Models with Enterprise BenchmarksBing Zhang, Mikio Takeuchi, Ryo Kawahara, Shubhi Asthana, Md. Maruf Hossain, Guang-Jie Ren, Kate Soule, Yifan Mai, Yada Zhu. 485-505 [doi]
• Can Post-Training Quantization Benefit from an Additional QLoRA Integration?Xiliang Zhu, Elena Khasanova, Cheng Chen. 506-514 [doi]
• From Generating Answers to Building Explanations: Integrating Multi-Round RAG and Causal Modeling for Scientific QAVictor Barres, Clifton James McFate, Aditya Kalyanpur, Kailash Karthik Saravanakumar, Lori Moon, Natnael Seifu, Abraham Bautista-Castillo. 515-522 [doi]
• TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in PracticeAman Goel, Xian Carrie Wu, Zhe Wang, Dmitriy Bespalov, Yanjun Qi. 523-534 [doi]
• Does Self-Attention Need Separate Weights in Transformers?Md Kowsher, Nusrat Jahan Prottasha, Chun-Nam Yu, Ozlem O. Garibay, Niloofar Yousefi. 535-543 [doi]
• SuperRAG: Beyond RAG with Layout-Aware Graph ModelingChening Yang, Duy-Khanh Vu, Minh-Tien Nguyen, Xuan Quang Nguyen, Linh Nguyen, Hung Le. 544-557 [doi]
• SweEval: Do LLMs Really Swear? A Safety Benchmark for Testing Limits for Enterprise UseHitesh Laxmichand Patel, Amit Agarwal, Arion Das, Bhargava Kumar, Srikant Panda, Priyaranjan Pattnayak, Taki Hasan Rafi, Tejaswini Kumar, Dong-Kyu Chae. 558-582 [doi]
• Natural Language Processing for Human Resources: A SurveyNaoki Otani, Nikita Bhutani, Estevam Hruschka. 583-597 [doi]
• Implementing Retrieval Augmented Generation Technique on Unstructured and Structured Data Sources in a Call Center of a Large Financial InstitutionSyed Shariyar Murtaza, Yifan Nie, Elias Avan, Utkarsh Soni, Wanyu Liao, Adam Carnegie, Cyril John Mathias, Junlin Jiang, Eugene Wen. 598-606 [doi]
• Granite Guardian: Comprehensive LLM SafeguardingInkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, Subhajit Chaudhury, Tejaswini Pedapati, Pierre L. Dognin, Keerthiram Murugesan, Erik Miehling, Martín Santillán Cooper, Kieran Fraser, Giulio Zizzo, Muhammad Zaid Hameed, Mark Purcell, Michael Desmond, Qian Pan, Inge Vejsbjerg, Elizabeth M. Daly, Michael Hind, Werner Geyer, Ambrish Rawat, Kush R. Varshney, Prasanna Sattigeri. 607-615 [doi]
• Breaking Down Power Barriers in On-Device Streaming ASR: Insights and SolutionsYang Li 0183, Yuan Shangguan, Yuhao Wang, Liangzhen Lai, Ernie Chang, Changsheng Zhao 0002, Yangyang Shi, Vikas Chandra. 616-626 [doi]
• Break-Ideate-Generate (BrIdGe): Moving beyond Translations for Localization using LLMsSwapnil Gupta, Lucas Pereira Carlini, Prateek Sircar, Deepak Gupta. 627-637 [doi]
• Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories PromptingEmmanuel Aboah Boateng, Cassiano O. Becker, Nabiha Asghar, Kabir Walia, Ashwin Srinivasan, Ehi Nosakhare, Soundar Srinivasan, Victor Dibia. 638-654 [doi]
• Towards Reliable Agents: Benchmarking Customized LLM-Based Retrieval-Augmented Generation Frameworks with Deployment ValidationKevin Shukang Wang, Karel Joshua Harjono, Ramon Lawrence. 655-661 [doi]
• Query Variant Detection Using Retriever as EnvironmentMinji Seo, Youngwon Lee 0003, Seung-won Hwang, Seoho Song, Hee-Cheol Seo, Young-In Song. 662-671 [doi]
• Evaluating Bias in LLMs for Job-Resume Matching: Gender, Race, and EducationHayate Iso, Pouya Pezeshkpour, Nikita Bhutani, Estevam Hruschka. 672-683 [doi]
• Goal-Driven Data Story, Narrations and ExplanationsAniya Aggarwal, Ankush Gupta, Shivangi Bithel, Arvind Agarwal. 684-694 [doi]
• VIT-Pro: Visual Instruction Tuning for Product ImagesVishnu Prabhakaran, Purav Aggarwal, Vishruit Kulshreshtha, Arunita Das, Sahini Venkata Sitaram Sruti, Anoop Saladi. 695-707 [doi]
• AutoKB: Automated Creation of Structured Knowledge Bases for Domain-Specific SupportRishav Sahay, Arihant Jain, Purav Aggarwal, Anoop Saladi. 708-723 [doi]
• Medical Spoken Named Entity RecognitionKhai Le-Duc, David Thulke, Hung Phong Tran, Long Vo-Dang, Khai-Nguyen Nguyen, Truong-Son Hy, Ralf Schlüter. 724-783 [doi]
• PLEX: Adaptive Parameter-Efficient Fine-Tuning for Code LLMs using Lottery-TicketsJaeseong Lee 0002, Hojae Han, Jongyoon Kim, Seung-won Hwang, Naun Kang, KyungJun An, Sungho Jang. 784-793 [doi]
• Evaluating the Performance of RAG Methods for Conversational AI in the Airport DomainYuyang Li, Philip J. M. Kerbusch, Raimon H. R. Pruim, Tobias Käfer. 794-808 [doi]
• LLM Safety for ChildrenPrasanjit Rath, Hari Shrawgi, Parag Agrawal, Sandipan Dandapat. 809-821 [doi]
• RxLens: Multi-Agent LLM-powered Scan and Order for PharmacyAkshay Jagatap, Srujana Merugu, Prakash Mandayam Comar. 822-832 [doi]
• Distill-C: Enhanced NL2SQL via Distilled Customization with LLMsCong Duy Vu Hoang, Gioacchino Tangari, Clémence Lanfranchi, Dalu Guo, Paul Cayet, Steve Siu, Don Dharmasiri, Yuan-Fang Li, Long Duong, Damien Hilloulin, Rhicheek Patra, Sungpack Hong, Hassan Chafi. 833-848 [doi]
• eC-Tab2Text: Aspect-Based Text Generation from e-Commerce Product TablesLuis Antonio Gutiérrez Guanilo, Mir Tafseer Nayeem, Cristian Jose Lopez Del Alamo, Davood Rafiei. 849-867 [doi]
• RAD-Bench: Evaluating Large Language Models' Capabilities in Retrieval Augmented DialoguesTzu-Lin Kuo, Fengting Liao, Mu-Wei Hsieh, Fu-Chieh Chang 0001, Po-Chun Hsu, Da-shan Shiu. 868-902 [doi]
• Conflict and Overlap Classification in Construction Standards Using a Large Language ModelSeong-Jin Park, Youn-Gyu Jin, Hyun-Young Moon, Bong-Hyuck Choi, Seung Hwan Lee, Ohjoon Kwon, Kang Min Kim. 903-917 [doi]
• Protein2Text: Resampling Mechanism to Translate Protein Sequences into Human-Interpretable TextAla Jararweh, Oladimeji Macaulay, David Arredondo, Yue Hu, Luis E. Tafoya, Kushal Virupakshappa, Avinash Sahu. 918-937 [doi]
• Cracking the Code: Multi-domain LLM Evaluation on Real-World Professional Exams in IndonesiaFajri Koto. 938-948 [doi]
• CodeGenWrangler: Data Wrangling task automation using Code-Generating ModelsAshlesha Akella, Abhijit Manatkar, Krishnasuri Narayanam, Sameep Mehta. 949-960 [doi]
• Dialogue Language Model with Large-Scale Persona Data EngineeringMengZe Hong, Chen Jason Zhang, Chaotao Chen, Rongzhong Lian, Di Jiang. 961-970 [doi]
• Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation ServiceSong Wang, Xun Wang, Jie Mei, Yujia Xie, Si-Qing Chen, Wayne Xiong. 971-978 [doi]
• Improved Near-Duplicate Detection for Aggregated and Paywalled News-FeedsSiddharth Tumre, Sangameshwar Patil, Alok Kumar. 979-987 [doi]
• Pisets: A Robust Speech Recognition System for Lectures and InterviewsIvan Bondarenko, Daniil Grebenkin, Oleg Sedukhin, Mikhail Klementev, Derunets Roman, Lyudmila Budneva. 988-997 [doi]
• CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial SearchKaixin Wu, Yixin Ji, Zeyuan Chen, Qiang Wang, Cunxiang Wang, Hong Liu, Baijun Ji, Jia Xu 0013, Zhongyi Liu, Jinjie Gu, Yuan Zhou, Linjian Mo. 998-1008 [doi]
• Schema and Natural Language Aware In-Context Learning for Improved GraphQL Query GenerationNitin Gupta 0005, Manish Kesarwani, Sambit Ghosh, Sameep Mehta, Carlos Eberhardt, Dan Debrunner. 1009-1015 [doi]
• Chatbot Arena Estimate: towards a generalized performance benchmark for LLM capabilitiesLucas Spangher, Tianle Li, William F. Arnold, Nick Masiewicki, Xerxes Dotiwalla, Rama Kumar Pasumarthi, Peter Grabowski, Eugene Ie, Daniel Gruhl. 1016-1025 [doi]
• Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language ModelsArvind Krishna Sridhar, Yinyi Guo, Erik Visser. 1026-1035 [doi]
• HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy ApplicationsRishi Kalra, Zekun Wu 0003, Ayesha Gulley, Airlie Hilliard, Xin Guan, Adriano S. Koshiyama, Philip C. Treleaven. 1036-1054 [doi]
• An Efficient Context-Dependent Memory Framework for LLM-Centric AgentsPengyu Gao, Jinming Zhao, Xinyue Chen, Yilin Long. 1055-1069 [doi]