arXiv cs.CL Computation and Language

Deepak Pandita, Flip Korn, Chris Welty, Christopher M. Homan: Forest vs Tree: The $(N, K)$ Trade-off in Reproducible ML Evaluation https://arxiv.org/abs/2508.03663 https://arxiv.org/pdf/2508.03663 https://arxiv.org/html/2508.03663

Johannes Niu, Mila Stillman, Anna Kruspe: OSINT or BULLSHINT? Exploring Open-Source Intelligence tweets about the Russo-Ukrainian War https://arxiv.org/abs/2508.03599 https://arxiv.org/pdf/2508.03599 https://arxiv.org/html/2508.03599

Muzhaffar Hazman, Susan McKeever, Josephine Griffith: Beyond Meme Templates: Limitations of Visual Similarity Measures in Meme Matching https://arxiv.org/abs/2508.03562 https://arxiv.org/pdf/2508.03562 https://arxiv.org/html/2508.03562

Antoine Chaffin, Rapha\"el Sourty: PyLate: Flexible Training and Retrieval for Late Interaction Models https://arxiv.org/abs/2508.03555 https://arxiv.org/pdf/2508.03555 https://arxiv.org/html/2508.03555

Wenlong Wu, Haofen Wang, Bohan Li, Peixuan Huang, Xinzhe Zhao, Lei Liang: MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generation https://arxiv.org/abs/2508.03553 https://arxiv.org/pdf/2508.03553 https://arxiv.org/html/2508.03553

Mohammadreza Sadeghi, Mahsa Ghazvini Nejad, MirHamed Jafarzadeh Asl, Yu Gu, Yuanhao Yu, Masoud Asgharian, Vahid Partovi Nia: MoKA: Mixture of Kronecker Adapters https://arxiv.org/abs/2508.03527 https://arxiv.org/pdf/2508.03527 https://arxiv.org/html/2508.03527

Alexander Golubev, et al.: Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning https://arxiv.org/abs/2508.03501 https://arxiv.org/pdf/2508.03501 https://arxiv.org/html/2508.03501

Hyungjin Kim, Seokho Ahn, Young-Duk Seo: Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models https://arxiv.org/abs/2508.03481 https://arxiv.org/pdf/2508.03481 https://arxiv.org/html/2508.03481

Michael K. Chen: A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning https://arxiv.org/abs/2508.03366 https://arxiv.org/pdf/2508.03366 https://arxiv.org/html/2508.03366

Yufei Xue, Yushi Huang, Jiawei Shao, Jun Zhang: VLMQ: Efficient Post-Training Quantization for Large Vision-Language Models via Hessian Augmentation https://arxiv.org/abs/2508.03351 https://arxiv.org/pdf/2508.03351 https://arxiv.org/html/2508.03351

Kisu Yang, Yoonna Jang, Hwanseok Jang, Kenneth Choi, Isabelle Augenstein, Heuiseok Lim: Reliable Evaluation Protocol for Low-Precision Retrieval https://arxiv.org/abs/2508.03306 https://arxiv.org/pdf/2508.03306 https://arxiv.org/html/2508.03306

Yubo Wang, Shimin Di, Zhili Wang, Haoyang Li, Fei Teng, Hao Xin, Lei Chen: Understanding the Embedding Models on Hyper-relational Knowledge Graph https://arxiv.org/abs/2508.03280 https://arxiv.org/pdf/2508.03280 https://arxiv.org/html/2508.03280

Junyoung Lim, Jaewoo Ahn, Gunhee Kim: ChartCap: Mitigating Hallucination of Dense Chart Captioning https://arxiv.org/abs/2508.03164 https://arxiv.org/pdf/2508.03164 https://arxiv.org/html/2508.03164

Zikun Cui, Tianyi Huang, Chia-En Chiang, Cuiqianhe Du: Toward Verifiable Misinformation Detection: A Multi-Tool LLM Agent Framework https://arxiv.org/abs/2508.03092 https://arxiv.org/pdf/2508.03092 https://arxiv.org/html/2508.03092

Zhu, Dou, Xi, Jin, Zhang, Zhang, Ye, Chai, Zhou, Zhang, Huang, Zhang, Wang, Gui: VRPO: Rethinking Value Modeling for Robust RL Training under Noisy Supervision https://arxiv.org/abs/2508.03058 https://arxiv.org/pdf/2508.03058 https://arxiv.org/html/2508.03058

Xinjie Zhao, et al.: AGENTiGraph: A Multi-Agent Knowledge Graph Framework for Interactive, Domain-Specific LLM Chatbots https://arxiv.org/abs/2508.02999 https://arxiv.org/pdf/2508.02999 https://arxiv.org/html/2508.02999

Peng Ding, Rick Stevens: Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling https://arxiv.org/abs/2508.02979 https://arxiv.org/pdf/2508.02979 https://arxiv.org/html/2508.02979

Boshi Huang, Fabio Nonato de Paula: Defend LLMs Through Self-Consciousness https://arxiv.org/abs/2508.02961 https://arxiv.org/pdf/2508.02961 https://arxiv.org/html/2508.02961

Vebj{\o}rn Haug K{\aa}sene, Pierre Lison: Following Route Instructions using Large Vision-Language Models: A Comparison between Low-level and Panoramic Action Spaces https://arxiv.org/abs/2508.02917 https://arxiv.org/pdf/2508.02917 https://arxiv.org/html/2508.02917

Rongxin Jiang, Robert Long, Chenghao Gu, Mingrui Yan: VisuCraft: Enhancing Large Vision-Language Models for Complex Visual-Guided Creative Content Generation via Structured Information Extrac... https://arxiv.org/abs/2508.02890 https://arxiv.org/pdf/2508.02890 https://arxiv.org/html/2508.02890

Qiang, Wang, Gong, Wang, Fu, Wang, Chen, Yi, Wen, Zhang, Wang, Dang, Tao: SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec https://arxiv.org/abs/2508.02849 https://arxiv.org/pdf/2508.02849 https://arxiv.org/html/2508.02849

Wenshuo Zhang, Leixian Shen, Shuchang Xu, Jindu Wang, Jian Zhao, Huamin Qu, Linping Yuan: NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification https://arxiv.org/abs/2508.02823 https://arxiv.org/pdf/2508.02823 https://arxiv.org/html/2508.02823

Yumeng Shi, Zhongliang Yang, DiYang Lu, Yisi Wang, Yiting Zhou, Linna Zhou: CreditARF: A Framework for Corporate Credit Rating with Annual Report and Financial Feature Integration https://arxiv.org/abs/2508.02738 https://arxiv.org/pdf/2508.02738 https://arxiv.org/html/2508.02738

Jean-Francois Chamberland, Martin C. Carlisle, Arul Jayaraman, Krishna R. Narayanan, Sunay Palsole, Karan Watson: Teaching at Scale: Leveraging AI to Evaluate and Elevate Engineering Education https://arxiv.org/abs/2508.02731 https://arxiv.org/pdf/2508.02731 https://arxiv.org/html/2508.02731

Wang, Hu, Liu, Zhu, Hou, Huang, Zhang, Yang, Liu, Zhang, Zhang, Wang, Jiang, Zhou: Efficient Agents: Building Effective Agents While Reducing Cost https://arxiv.org/abs/2508.02694 https://arxiv.org/pdf/2508.02694 https://arxiv.org/html/2508.02694

Peng Ding: ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs https://arxiv.org/abs/2507.10593 https://arxiv.org/pdf/2507.10593 https://arxiv.org/html/2507.10593

Liu, Liu, Liu, Xiao, Gao, Lyu, Gu, Zhang, Wong, Zhang, Chen: CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward https://arxiv.org/abs/2508.03686 https://arxiv.org/pdf/2508.03686 https://arxiv.org/html/2508.03686

Yangtian Zi, Harshitha Menon, Arjun Guha: More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation https://arxiv.org/abs/2508.03678 https://arxiv.org/pdf/2508.03678 https://arxiv.org/html/2508.03678

Arturo P\'erez-Peralta, Sandra Ben\'itez-Pe\~na, Rosa E. Lillo: FairLangProc: A Python package for fairness in NLP https://arxiv.org/abs/2508.03677 https://arxiv.org/pdf/2508.03677 https://arxiv.org/html/2508.03677

Li, Geng, Xiong, He, Hu, Chen, Chen, Chang, Zhang, Mo, Li, Yuan, Sun: CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction https://arxiv.org/abs/2508.03668 https://arxiv.org/pdf/2508.03668 https://arxiv.org/html/2508.03668