Table of Contents

• Iterative Structured Pruning for Large Language Models with Multi-Domain CalibrationGuangxin Wu, Hao Zhang, Zhibin Zhang, Jiafeng Guo, Xueqi Cheng. 1-10 [doi]
• SCRIPTMIND: Crime Script Inference and Cognitive Evaluation for LLM-based Social Engineering Scam Detection SystemHeedou Kim, Changsik Kim, Sanghwa Shin, Jaewoo Kang. 11-38 [doi]
• From Paper to Structured JSON: An Agentic AI Workflow for Compliant BMR Digital TransformationBhavik Agarwal, Nidhi Bendre, Viktoria Rojkova. 39-47 [doi]
• Compact Multimodal Language Models as Robust OCR Alternatives for Noisy Textual Clinical ReportsNikita Neveditsin, Pawan Lingras, Salil Patil, Swarup Patil, Vijay Kumar Mago. 48-59 [doi]
• PersonaTrace: Synthesizing Realistic Digital Footprints with LLM AgentsMinjia Wang, Yunfeng Wang, Xiao Ma, Dexin Lv, Qifan Guo, Lynn Zheng, Benliang Wang, Lei Wang, Jiannan Li, Yongwei Xing, Junzhe Xu, Zheng Sun. 60-77 [doi]
• Evaluating the Pre-Consultation Ability of LLMs using Diagnostic GuidelinesJean Seo, Gibaeg Kim, Kihun Shin, Seungseop Lim, Hyunkyung Lee, Wooseok Han, Jongwon Lee, Eunho Yang. 78-94 [doi]
• SELENE: Selective and Evidence-Weighted LLM Debating for Efficient and Reliable ReasoningAkshay Verma, Swapnil Gupta, Deepak Gupta, Prateek Sircar, Siddharth Pillai. 95-104 [doi]
• SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python CodeShima Imani, Seungwhan Moon, Adel Ahmadyan, Lu Zhang, Ahmed Kirmani, Babak Damavandi. 105-118 [doi]
• KV Pareto: Systems-Level Optimization of KV Cache and Model Compression for Long Context InferenceSai Gokhale, Devleena Das, Rajeev Patwari, Ashish Sirasao, Elliott Delaye. 119-131 [doi]
• MizanQA: A Benchmark for Multi-Answer Moroccan Legal QAAdil Bahaj, Mounir Ghogho. 132-144 [doi]
• Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded DialogsSandeep Mishra, Devichand Budagam, Anubhab Mandal, Bishal Santra, Pawan Goyal 0002, Manish Gupta 0001. 145-156 [doi]
• Beyond Unified Models: A Service-Oriented Approach to Low Latency, Context Aware Phonemization for Real Time TTSMahta Fetrat Qharabagh, Donya Navabi, Zahra Dehghanian, Morteza Abolghasemi, Hamid R. Rabiee 0001. 157-168 [doi]
• Retrieval Enhancements for RAG: Insights from a Deployed Customer Support ChatbotDaniel González Juclà, Mohit Tuteja, Marcos Esteve Casademunt, Keshav Unnikrishnan, Yasir Usmani, Arvind Roshaan. 169-180 [doi]
• Scaling Intent Understanding: A Framework for Classification with Clarification using Lightweight LLMsSubhadip Nandi, Tanishka Agarwal, Anshika Singh, Priyanka Bhatt. 181-192 [doi]
• Beyond IVR: Benchmarking Customer Support LLM Agents for Business-AdherenceSumanth Balaji, Piyush Mishra, Aashraya Sachdeva, Suraj Agrawal. 193-208 [doi]
• HotelQuEST: Balancing Quality and Efficiency in Agentic SearchGuy Hadad, Shadi Iskander, Sofia Tolmach, Oren Kalinsky, Haggai Roitman, Ran Levy. 209-225 [doi]
• TASER: Table Agents for Schema-guided Extraction and RecommendationNicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso. 226-252 [doi]
• TAGQuant: Token-Aware Clustering for Group-Wise QuantizationJaeseong Lee 0002, Seung-won Hwang, Aurick Qiao, Zhewei Yao, Yuxiong He. 253-262 [doi]
• Beyond Grid Search: Leveraging Bayesian Optimization for Accelerating RAG Pipeline OptimizationAnum Afzal, Xueru Zheng, Florian Matthes. 263-277 [doi]
• BornoDrishti: Leveraging Vision Encoders and Domain-Adaptive Learning for Bangla OCR on Diverse DocumentsS. M. Jishanul Islam, Md Mehedi Hasan, Masbul Haider Ovi, AKM Shahariar Azad Rabby, Fuad Rahman 0001. 278-286 [doi]
• MobileCity: An Efficient Framework for Large-Scale Urban Behavior SimulationXiaotong Ye, Nicolas Bougie, Toshihiko Yamasaki, Narimawa Watanabe. 287-303 [doi]
• Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and BottlenecksMasaya Tsunokake, Yuta Koreeda, Terufumi Morishita, Koichi Nagatsuka, Hikaru Tomonari, Yasuhiro Sogawa. 304-316 [doi]
• A Compliance-Preserving Retrieval System for Aircraft MRO Task SearchByungho Jo. 317-329 [doi]
• No Label? No Problem: Unsupervised Continual Learning for Adaptive Medical ASRMeizhu Liu, Tao Sheng. 330-337 [doi]
• EduPulse: A Practical LLM-Enhanced Opinion Mining System for Vietnamese Student Feedback in Educational PlatformsNguyen Xuan Phuc, Phi Nguyen Xuan, Vinh-Tiep Nguyen, Thìn Dang Van, Ngan Luu-Thuy Nguyen. 338-365 [doi]
• When Speed Meets Intelligence: Scalable Conversational NER in an Ever-evolving WorldKarim Ghonim, Antonio Roberto, Davide Bernardi. 366-376 [doi]
• ReflectiveRAG: Rethinking Adaptivity in Retrieval-Augmented GenerationAkshay Verma, Swapnil Gupta, Siddharth Pillai, Prateek Sircar, Deepak Gupta. 377-384 [doi]
• OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale DatasetsJiyuan Shen, Yuan Peiyue, Atin Ghosh, Yifan Mai 0001, Daniel Dahlmeier. 385-396 [doi]
• PatentVision: A multimodal method for drafting patent applicationsRuo Yang, Sai Krishna Reddy Mudhiganti, Manali Sharma. 397-405 [doi]
• VideoMind: Thinking in Steps for Long Video UnderstandingShubhang Bhatnagar, Renxiong Wang, Kapil Krishnakumar, Adel Ahmadyan, Zhaojiang Lin, Lambert Mathias, Xin Luna Dong, Babak Damavandi, Narendra Ahuja, Seungwhan Moon. 406-416 [doi]
• RegNLI: Detecting Online Product Misbranding through Legal and Linguistic AlignmentDiya Saha, Abhishek Bharadwaj Varanasi, Tirthankar Dasgupta, Manjira Sinha. 417-424 [doi]
• CASPER: Bridging Discrete and Continuous Prompt Optimization through Feedback-Guided Gradient DescentAryan Jain, Pushpendu Ghosh, Promod Yenigalla. 425-437 [doi]
• Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent ImprovementAaditya Shukla, Sidney Knowles, Meenakshi Madugula, David Farris, Ryan Angilly, Santiago Pombo, Lu An, Anbang Xu, Abhinav Balasubramanian, Tan Yu, Jiaxiang Ren 0004, Rama Akkiraju. 438-454 [doi]
• Medical Summarization in Practice: Design, Deployment, and Analysis of a Clinical Summarization System for a German HospitalMoiz Rauf, Sean Papay. 455-466 [doi]
• Feedback-Aware Prompt Optimization Framework for Generating Job PostingsSuraj Maharjan, Ainur Yessenalina, Srinivasan H. Sengamedu. 467-474 [doi]
• Enhancing User Safety: Context-Aware Detection of Offensive Query-Ad Pairs in Multimodal Search AdvertisingGaurav Kumar, Qiangjian Xi, Tanmaya Shekhar Dabral, Hooshang Ghasemi, Abishek Krishnamoorthy, Danqing Fu, Rui Min, Emilio R. Antúnez, Zhongli Ding, Pradyumna Narayana. 475-482 [doi]
• SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language ModelsJiaojiao Han, Wujiang Xu, Mingyu Jin, Mengnan Du. 483-495 [doi]
• Adapting Vision-Language Models for E-commerce Understanding at ScaleMatteo Nulli, Orshulevich Vladimir, Tala Bazazo, Christian Herold, Michael Kozielski, Marcin Mazur, Szymon Tuzel, Cees G. M. Snoek, Seyyed Hadi Hashemi, Omar Javed, Yannick Versley, Shahram Khadivi. 496-512 [doi]
• MedRiskEval: Medical Risk Evaluation Benchmark of Language Models, On the Importance of User Perspectives in Healthcare SettingsJean-Philippe Corbeil, Minseon Kim, Maxime Griot, Sheela Agarwal, Alessandro Sordoni, François Beaulieu, Paul Vozila. 513-524 [doi]
• Synthetic Doctor-Patient Dialogue Generation for Robust Medical ASR: A Scalable Pipeline for Vocabulary Expansion and Privacy PreservationKefei Liu 0001, Meizhu Liu. 525-534 [doi]
• Lessons from the Field: An Adaptable Lifecycle Approach to Applied Dialogue SummarizationKushal Chawla, Chenyang Zhu 0011, Pengshan Cai, Sangwoo Cho, Scott Novotney, Ayushman Singh, Jonah Lewis, Keasha Safewright, Alfy Samuel, Erin Babinsky, Shi-Xiong Zhang, Sambit Sahu. 535-544 [doi]
• LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call TranscriptsSeyedali Mohammadi, Manas Paldhe, Amit Chhabra, Youngseo Son, Vishal Seshagiri. 545-561 [doi]
• Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model MergingAlphaeus Dmonte, Vidhi Gupta, Daniel J. Perry, Mark Arehart. 562-570 [doi]
• The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent SystemsDevang Kulshreshtha, Wanyu Du, Raghav Jain, Srikanth Doss, Hang Su, Sandesh Swamy, Yanjun Qi. 571-585 [doi]
• Tailoring Rumor Debunking to You: Diversifying Chinese Rumor-Debunking Passages with an LLM-Driven Simulated Feedback-Enhanced FrameworkXinle Pang, Danding Wang, Qiang Sheng 0001, Yifan Sun, Beizhe Hu, Juan Cao 0001. 586-597 [doi]
• Synthetic Data Fine-Tuning for Effective Team Formation in EnterprisesGuilherme Drummond Lima, Adriano Veloso. 598-609 [doi]
• Assertion-Conditioned Compliance: A Provenance-Aware Vulnerability in Multi-Turn Tool-Calling AgentsDaud Waqas, Aaryamaan Golthi, Erika Hayashida, Huanzhi Mao. 610-624 [doi]
• PROBES : Performance and Relevance Observation for BEtter SearchSejal Jain, Cyrus Andre DSouza, Jitenkumar Babubhai Rana, Aniket Joshi, Promod Yenigalla. 625-635 [doi]
• Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement LearningMinseok Kim, Jingxiang Chen, Seong-Gyun Leem, Yin Huang, Rashi Rungta, Zhicheng Ouyang, Haibin Wu, Surya Teja Appini, Ankur Bansal, Yang Bai, Yue Liu, Florian Metze, Ahmed Aly, Anuj Kumar, Ariya Rastrow, Zhaojiang Lin. 636-648 [doi]
• IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian LanguagesPriyaranjan Pattnayak, Sanchari Chowdhuri. 649-668 [doi]
• Synthesizing question answering data from financial documents: An End-to-End Multi-Agent ApproachChetan Harsha, Karmvir Singh Phogat, Sridhar Dasaratha, Shashishekar Ramakrishna. 669-687 [doi]
• Toward Automatic Delegation Extraction in Japanese LawTsuyoshi Fujita, Yuya Sawada, Yusuke Sakai 0010, Taro Watanabe. 688-710 [doi]
• DIALECTIC: A Multi-Agent System for Startup EvaluationJae-Yoon Bae, Simon Malberg, Joyce Ann Clarize Galang, Andre Retterath, Georg Groh. 711-727 [doi]
• Long-Context Long-Form Question Answering for Legal DomainAnagha Kulkarni 0006, Parin Rajesh Jhaveri, Prasha Shrestha, Yu Tong Han, Reza Amini, Behrouz Madahian. 728-751 [doi]
• ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMsHangyeol Yoo, ChangSu Choi, MinJun Kim, Seohyun Song, Seungwoo Song, Inho Won, Jongyoul Park, Cheoneum Park, Kyungtae Lim. 752-763 [doi]
• MIRAGE: Metadata-guided Image Retrieval and Answer Generation for E-commerce TroubleshootingRishav Sahay, Lavanya Sita Tekumalla, Anoop Saladi. 764-776 [doi]
• CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL OptimizationChe-Ming Chang, Prashanth Vijayaraghavan, Ashutosh Jadhav, Charles Mackin, Hsinyu Tsai, Vandana V. Mukherjee, Ehsan Degan. 777-788 [doi]
• D3: Dynamic Docid Decoding for Multi-Intent Generative RetrievalJaeyoung Kim, Dohyeon Lee, Soona Hong, Seung-won Hwang. 789-800 [doi]
• DisGraph-RP: Graph-Augmented Temporal Modeling with Aspect-Based Contrastive Encoding of Discharge Summary for Readmission PredictionSudeshna Jana, Tirthankar Dasgupta, Manjira Sinha, Pabitra Mitra. 801-812 [doi]
• CareerPathKG: Knowledge Graph Integrated Framework for Career IntelligenceNgoc-Quang Le, Duc Duong Hoang, Mai-Vu Tran, Thi-Hai-Yen Vuong. 813-822 [doi]
• A Hybrid Supervised-LLM Pipeline for Actionable Suggestion Mining in Unstructured Customer ReviewsAakash Trivedi, Aniket Upadhyay, Pratik Narang, Dhruv Kumar 0001, Praveen Kumar. 823-836 [doi]
• ShopperBench: A Benchmark for Personalized Shopping with Persona-Guided SimulationYuan Ling, Chunqing Yuan, Shujing Dong, Yongjian Yang, Nataraj Mocherla, Ayush Goyal. 837-846 [doi]
• ARQA: A Benchmark for Grounded Table-Text QA in Enterprise Annual ReportsRuilong Wang, Simone Balloccu. 847-868 [doi]
• Do Clinical Question Answering Systems Really Need Specialised Medical Fine Tuning?Sushant Kumar Ray, Gautam Siddharth Kashyap, Sahil Tripathi, Nipun Joshi, Vijay Govindarajan, Rafiq Ali, Jiechao Gao, Usman Naseem. 869-876 [doi]
• SkiLLens: Recognising and Mapping Novel Skills from Millions of Job Ads Across Europe Using Language ModelsAlessia De Santo, Lorenzo Malandri, Fabio Mercorio, Mario Mezzanzanica, Navid Nobani. 877-885 [doi]
• SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and SummarizationPrashanth Vijayaraghavan, Apoorva Nitsure, Luyao Shi, Charles Mackin, Ashutosh Jadhav, David Beymer, Ehsan Degan, Vandana V. Mukherjee. 886-899 [doi]
• Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal ReflectionZhiyu Xue, Reza Abbasi-Asl, Ramtin Pedarsani. 900-914 [doi]
• Lightweight Domain-Specific Language Model for Real-Time Structuring of Medical PrescriptionsJonathan Pattin Cottet, Véronique Eglin, Alex Aussem. 915-926 [doi]
• Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden's J statisticStephane Collot, Colin Fraser, Justin Zhao, William F. Shen, Timon Willi, Ilias Leontiadis. 927-936 [doi]
• PharmaQA.IT: an Italian dataset for Q&A in the pharmaceutical domainKamyar Zeinalipour, Andrea Zugarini, Asya Zanollo, Leonardo Rigutini. 937-947 [doi]
• DIRECT: Directional Relevance in Conversational TrajectoriesAnshuman Mourya, Rajdeep Mukherjee, Prerna Jolly, Vinayak S. Puranik, Sivaramakrishnan R. Kaveri. 948-957 [doi]