Table of Contents

• HPipe: Large Language Model Pipeline Parallelism for Long Context on Heterogeneous Cost-effective DevicesRuilong Ma, Xiang Yang, Jing Wang 0039, Qi Qi 0001, Haifeng Sun 0001, Zirui Zhuang, Jianxin Liao. 1-9 [doi]
• Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel DecodingJie Ou, Yueming Chen, Prof. Tian. 10-22 [doi]
• SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-ScalingSanghoon Kim, DahYun Kim, Chanjun Park, Wonsung Lee, Wonho Song, Yunsu Kim 0004, Hyeonwoo Kim, Yungi Kim, Hyeonju Lee, Jihoo Kim, Changbae Ahn, Seonghoon Yang, Sukyung Lee, Hyunbyung Park, Gyoungjin Gim, Mikyoung Cha, Hwalsuk Lee, Sunghun Kim. 23-35 [doi]
• UINav: A Practical Approach to Train On-Device Automation AgentsWei Li, Fu-Lin Hsu, William Bishop, Folawiyo Campbell-Ajala, Max Lin, Oriana Riva. 36-51 [doi]
• Efficiently Distilling LLMs for Edge ApplicationsAchintya Kundu, Fabian Lim, Aaron Chew, Laura Wynter, Penny Chong, Rhui Dih Lee. 52-62 [doi]
• Modeling and Detecting Company Risks from NewsJiaxin Pei, Soumya Vadlamannati, Liang-Kang Huang, Daniel Preotiuc-Pietro, Xinyu Hua. 63-72 [doi]
• Multiple-Question Multiple-Answer Text-VQAPeng Tang, Srikar Appalaraju, R. Manmatha, Yusheng Xie, Vijay Mahadevan. 73-88 [doi]
• An NLP-Focused Pilot Training Agent for Safe and Efficient Aviation CommunicationXiaochen Liu, Bowei Zou, AiTi Aw. 89-96 [doi]
• Visual Grounding for User InterfacesYijun Qian, Yujie Lu, Alexander Hauptmann 0001, Oriana Riva. 97-107 [doi]
• Prompt Tuned Embedding Classification for Industry Sector AllocationValentin Leonhard Buchner, Lele Cao, Jan-Christoph Kalo, Vilhelm von Ehrenheim. 108-118 [doi]
• REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity LinkingNacime Bouziani, Shubhi Tyagi, Joseph Fisher, Jens Lehmann 0001, Andrea Pierleoni. 119-130 [doi]
• Conformer-Based Speech Recognition On Extreme Edge-Computing DevicesMingbin Xu, Alex Jin, Sicheng Wang, Mu Su, Tim Ng, Henry Mason, Shiyi Han, Zhihong Lei, Yaqiao Deng, Zhen Huang 0001, Mahesh Krishnamoorthy. 131-139 [doi]
• Generating Signed Language Instructions in Large-Scale Dialogue SystemsMert Inan, Katherine Atwell, Anthony Sicilia, Lorna C. Quandt, Malihe Alikhani. 140-154 [doi]
• Leveraging Natural Language Processing and Large Language Models for Assisting Due Diligence in the Legal DomainMyeongjun Jang, Gábor Stikkel. 155-164 [doi]
• AnnoLLM: Making Large Language Models to Be Better Crowdsourced AnnotatorsXingwei He 0003, Zhenghao Lin, Yeyun Gong, A-Long Jin, Hang Zhang 0029, Chen Lin 0001, Jian Jiao 0007, Siu-Ming Yiu, Nan Duan, Weizhu Chen. 165-190 [doi]
• An Automatic Prompt Generation System for Tabular Data TasksAshlesha Akella, Abhijit Manatkar, Brijkumar Chavda, Hima Patel. 191-200 [doi]
• Fighting crime with Transformers: Empirical analysis of address parsing methods in payment dataHaitham Hammami, Louis Baligand, Bojan Petrovski. 201-212 [doi]
• Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage DomainBrian Hu 0001, Bill Ray, Alice Leung, Amy Summerville, David Joy, Christopher Funk, Arslan Basharat. 213-227 [doi]
• Reducing hallucination in structured outputs via Retrieval-Augmented GenerationOrlando Ayala, Patrice Béchard. 228-238 [doi]
• Towards Translating Objective Product Attributes Into Customer LanguageRam Yazdi, Oren Kalinsky, Alexander Libov, Dafna Shahaf. 239-247 [doi]
• Automating the Generation of a Functional Semantic Types Ontology with Foundational ModelsSachin Konan, Larry Rudolph, Scott Affens. 248-265 [doi]
• Leveraging Customer Feedback for Multi-modal Insight ExtractionSandeep Sricharan Mukku, Abinesh Kanagarajan, Pushpendu Ghosh, Chetan Aggarwal. 266-278 [doi]
• Optimizing LLM Based Retrieval Augmented Generation Pipelines in the Financial DomainYiyun Zhao, Prateek Singh, Hanoz Bhathena, Bernardo Ramos, Aviral Joshi, Swaroop Gadiyaram, Saket Sharma. 279-294 [doi]
• Scaling Up Authorship AttributionJacob Striebel, Abishek Edikala, Ethan Irby, Alex Rosenfeld, J. Gage, Daniel Dakota, Sandra Kübler. 295-302 [doi]
• Multimodal Contextual Dialogue Breakdown Detection for Conversational AI ModelsMd Messal Monem Miah, Ulie Schnaithmann, Arushi Raghuvanshi, Youngseo Son. 303-314 [doi]
• Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASRZelin Wu, Gan Song, Christopher Li, Pat Rondon, Zhong Meng, Xavier Velez, Weiran Wang, Diamantino Caseiro, Golan Pundak, Tsendsuren Munkhdalai, Angad Chandorkar, Rohit Prabhavalkar. 315-323 [doi]
• Less is More for Improving Automatic Evaluation of Factual ConsistencyTong Wang, Ninad Kulkarni, Yanjun Qi. 324-334 [doi]
• DriftWatch: A Tool that Automatically Detects Data Drift and Extracts Representative Examples Affected by DriftMyeongjun Jang, Antonios Georgiadis, Yiyun Zhao, Fran Silavong. 335-346 [doi]
• Graph Integrated Language Transformers for Next Action Prediction in Complex Phone CallsAmin Hosseiny Marani, Ulie Schnaithmann, Youngseo Son, Akil Iyer, Manas Paldhe, Arushi Raghuvanshi. 347-358 [doi]
• Leveraging LLMs for Dialogue Quality MeasurementJinghan Jia, Abi Komma, Timothy Leffel, Xujun Peng, Ajay Nagesh, Tamer Soliman, Aram Galstyan, Anoop Kumar. 359-367 [doi]
• Uncertainty Estimation in Large Language Models to Support Biodiversity ConservationMaria Mora-Cross, Saúl Calderón Ramírez. 368-378 [doi]
• AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility PredictionShengkun Wang, Taoran Ji, Jianfeng He, Mariam Almutairi, Dan Wang, Linhan Wang, Min Zhang, Chang-Tien Lu. 379-386 [doi]
• Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?Xue-Yong Fu, Md. Tahmid Rahman Laskar, Elena Khasanova, Cheng Chen, Shashi Bhushan TN. 387-394 [doi]
• Shears: Unstructured Sparsity with Neural Low-rank Adapter SearchJ. Pablo Muñoz, Jinjie Yuan, Nilesh Jain. 395-405 [doi]
• Tree-of-Question: Structured Retrieval Framework for Korean Question Answering SystemsDongyub Lee, Younghun Jeong, Hwa-Yeon Kim, HongYeon Yu, Seunghyun Han, Taesun Whang, Seungwoo Cho, Chanhee Lee, Gunsu Lee, Youngbum Kim. 406-418 [doi]
• LLM-based Frameworks for API Argument Filling in Task-Oriented Conversational SystemsJisoo Mok, Mohammad Kachuee, Shuyang Dai, Shayan Ray, Tara Taghavi, Sungroh Yoon. 419-426 [doi]
• Large Language Models Encode the Practice of MedicineTeja Kanchinadam, Shaheen Gauher. 427-436 [doi]
• Leveraging Interesting Facts to Enhance User Engagement with Conversational InterfacesNikhita Vedula, Giuseppe Castellucci, Eugene Agichtein, Oleg Rokhlenko, Shervin Malmasi. 437-446 [doi]
• Search Query Refinement for Japanese Named Entity Recognition in E-commerce DomainYuki Nakayama, Ryutaro Tatsushima, Erick Mendieta, Koji Murakami, Keiji Shinzato. 447-452 [doi]
• EIVEN: Efficient Implicit Attribute Value Extraction using Multimodal LLMHenry Peng Zou, Gavin Heqing Yu, Ziwei Fan, Dan Bu, Han Liu, Peng Dai, Dongmei Jia, Cornelia Caragea. 453-463 [doi]
• Exploring the Impact of Table-to-Text Methods on Augmenting LLM-based Question Answering with Domain Hybrid DataDehai Min, Nan Hu, Rihui Jin, Nuo Lin, Jiaoyan Chen 0001, Yongrui Chen 0002, Yu Li, Guilin Qi, Yun Li, Nijun Li, Qianren Wang. 464-482 [doi]
• Solving General Natural-Language-Description Optimization Problems with Large Language ModelsJihai Zhang, Wei Wang, Siyan Guo, Li Wang, Fangquan Lin, Cheng Yang, Wotao Yin. 483-490 [doi]
• Self-Regulated Data-Free Knowledge Amalgamation for Text ClassificationPrashanth Vijayaraghavan, Hongzhi Wang 0002, Luyao Shi, Tyler Baldwin, David Beymer, Ehsan Degan. 491-502 [doi]