Computation and Language

Authors and titles for October 2025

[1] arXiv:2510.00125 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning Show Chinese title

Title: 直接标记优化：一种大语言模型遗忘的自包含方法

Hong kyu Lee, Ruixuan Liu, Li Xiong

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR)

[2] arXiv:2510.00161 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: TAMA: Tool-Augmented Multimodal Agent for Procedural Activity Understanding Show Chinese title

Title: TAMA：用于过程活动理解的工具增强型多模态代理

Kimihiro Hasegawa, Wiradee Imrattanatrai, Masaki Asada, Ken Fukuda, Teruko Mitamura

Comments: 21 pages. Code: https://github.com/kimihiroh/tama

Subjects: Computation and Language (cs.CL)

[3] arXiv:2510.00172 (cross-list from cs.CL) [cn-pdf, pdf, other]

Title: DRBench: A Realistic Benchmark for Enterprise Deep Research Show Chinese title

Title: DRBench：企业深度研究的现实基准

Amirhossein Abaskohi, Tianyi Chen, Miguel Muñoz-Mármol, Curtis Fox, Amrutha Varshini Ramesh, Étienne Marcotte, Xing Han Lù, Nicolas Chapados, Spandana Gella, Christopher Pal, Alexandre Drouin, Issam H. Laradji

Subjects: Computation and Language (cs.CL)

[4] arXiv:2510.00174 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: PrimeX: A Dataset of Worldview, Opinion, and Explanation Show Chinese title

Title: PrimeX：一个世界观、观点和解释的数据集

Rik Koncel-Kedziorski, Brihi Joshi, Tim Paek

Comments: EMNLP 2025 Main

Subjects: Computation and Language (cs.CL)

[5] arXiv:2510.00177 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Personalized Reasoning: Just-In-Time Personalization and Why LLMs Fail At It Show Chinese title

Title: 个性化推理：即时个性化与大语言模型为何在此失败

Shuyue Stella Li, Avinandan Bose, Faeze Brahman, Simon Shaolei Du, Pang Wei Koh, Maryam Fazel, Yulia Tsvetkov

Comments: 57 pages, 6 figures

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)

[6] arXiv:2510.00232 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses Show Chinese title

Title: BiasFreeBench：一种用于减轻大型语言模型响应中偏见的基准

Xin Xu, Xunzhi He, Churan Zhi, Ruizhe Chen, Julian McAuley, Zexue He

Comments: Work in progress

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY) ; Machine Learning (cs.LG)

[7] arXiv:2510.00255 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: TASER: Translation Assessment via Systematic Evaluation and Reasoning Show Chinese title

Title: TASER：通过系统评估和推理进行翻译评估

Monishwaran Maheswaran, Marco Carini, Christian Federmann, Tony Diaz

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)

[8] arXiv:2510.00261 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Retrieval-Augmented Generation for Electrocardiogram-Language Models Show Chinese title

Title: 增强检索的生成用于心电图-语言模型

Xiaoyu Song, William Han, Tony Chen, Chaojing Duan, Michael A. Rosenberg, Emerson Liu, Ding Zhao

Comments: 5 pages, 2 figures; Submitted to ICASSP 2026

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) ; Multimedia (cs.MM)

[9] arXiv:2510.00263 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Judging with Confidence: Calibrating Autoraters to Preference Distributions Show Chinese title

Title: 自信判断：校准自动评分器以适应偏好分布

Zhuohang Li, Xiaowei Li, Chengyu Huang, Guowang Li, Katayoon Goshvadi, Bo Dai, Dale Schuurmans, Paul Zhou, Hamid Palangi, Yiwen Song, Palash Goyal, Murat Kantarcioglu, Bradley A. Malin, Yuan Xue

Subjects: Computation and Language (cs.CL)

[10] arXiv:2510.00268 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction Show Chinese title

Title: 用于修订意图预测的高效逐层大语言模型微调

Zhexiong Liu, Diane Litman

Comments: In The Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2025

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)

[11] arXiv:2510.00276 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: SafePassage: High-Fidelity Information Extraction with Black Box LLMs Show Chinese title

Title: SafePassage：使用黑盒LLMs的高保真信息提取

Joe Barrow, Raj Patel, Misha Kharkovski, Ben Davies, Ryan Schmitt

Subjects: Computation and Language (cs.CL) ; Machine Learning (cs.LG)

[12] arXiv:2510.00280 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgment Show Chinese title

Title: ReEvalMed：通过将评估指标与现实临床判断对齐来重新思考医学报告评估

Ruochen Li, Jun Li, Bailiang Jian, Kun Yuan, Youxiang Zhu

Subjects: Computation and Language (cs.CL)

[13] arXiv:2510.00288 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: o-MEGA: Optimized Methods for Explanation Generation and Analysis Show Chinese title

Title: o-MEGA：优化的解释生成和分析方法

Ľuboš Kriš, Jaroslav Kopčan, Qiwei Peng, Andrej Ridzik, Marcel Veselý, Martin Tamajka

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)

[14] arXiv:2510.00311 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: CORTEX: Collaborative LLM Agents for High-Stakes Alert Triage Show Chinese title

Title: CORTEX：高风险警报分类的协作大语言模型代理

Bowen Wei, Yuan Shen Tay, Howard Liu, Jinhao Pan, Kun Luo, Ziwei Zhu, Chris Jordan

Subjects: Computation and Language (cs.CL)

[15] arXiv:2510.00444 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: TokMem: Tokenized Procedural Memory for Large Language Models Show Chinese title

Title: TokMem：大型语言模型的分词过程记忆

Zijun Wu, Yongchang Hao, Lili Mou

Subjects: Computation and Language (cs.CL)

[16] arXiv:2510.00446 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: LongCodeZip: Compress Long Context for Code Language Models Show Chinese title

Title: LongCodeZip：为代码语言模型压缩长上下文

Yuling Shi, Yichun Qian, Hongyu Zhang, Beijun Shen, Xiaodong Gu

Comments: Accepted to ASE 2025. Code available at https://github.com/YerbaPage/LongCodeZip

Subjects: Computation and Language (cs.CL) ; Software Engineering (cs.SE)

[17] arXiv:2510.00449 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews Show Chinese title

Title: 使用上下文用户评论增强评分预测的现成大语言模型

Koki Ryu, Hitomi Yanaka

Comments: Accepted to EMNLP 2025 PALS Workshop

Subjects: Computation and Language (cs.CL)

[18] arXiv:2510.00482 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Agent Fine-tuning through Distillation for Domain-specific LLMs in Microdomains Show Chinese title

Title: 通过蒸馏进行代理微调，用于微领域中的领域特定大语言模型

Yawen Xue, Masaya Tsunokake, Yuta Koreeda, Ekant Muljibhai Amin, Takashi Sumiyoshi, Yasuhiro Sogawa

Comments: Accepted by AIxB 2025

Subjects: Computation and Language (cs.CL)

[19] arXiv:2510.00496 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations Show Chinese title

Title: Agent-ScanKit：通过敏感性扰动解密多模态代理的内存和推理

Pengzhou Cheng, Lingzhong Dong, Zeng Wu, Zongru Wu, Xiangru Tang, Chengwei Qin, Zhuosheng Zhang, Gongshen Liu

Comments: 23 pages, 10 figures, 7 tables

Subjects: Computation and Language (cs.CL)

[20] arXiv:2510.00499 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance Show Chinese title

Title: MOSS-语音：无需文本指导的真实语音到语音模型

Xingjian Zhao, Zhe Xu, Qinyuan Cheng, Zhaoye Fei, Luozhijie Jin, Yang Wang, Hanfu Chen, Yaozhou Jiang, Qinghui Gao, Ke Chen, Ruixiao Li, Mingshu Chen, Ruiming Wang, Wenbo Zhang, Yiyang Zhang, Donghua Yu, Yang Gao, Xiaogui Yang, Yitian Gong, Yuanfan Xu, Yaqian Zhou, Xuanjing Huang, Xipeng Qiu

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)

[21] arXiv:2510.00507 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs Show Chinese title

Title: Graph2Eval：通过知识图谱为代理自动生成多模态任务

Yurun Chen, Xavier Hu, Yuhan Liu, Ziqi Wang, Zeyi Liao, Lin Chen, Feng Wei, Yuxi Qian, Bo Zheng, Keting Yin, Shengyu Zhang

Comments: 20 pages, 10 figures. Our Code: https://github.com/YurunChen/Graph2Eval

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)

[22] arXiv:2510.00508 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Copy-Paste to Mitigate Large Language Model Hallucinations Show Chinese title

Title: 复制粘贴以减轻大型语言模型的幻觉

Yongchao Long, Xian Wu, Yingying Zhang, Xianbin Wen, Yuxi Zhou, Shenda Hong

Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI)

[23] arXiv:2510.00510 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: JoyAgent-JDGenie: Technical Report on the GAIA Show Chinese title

Title: JoyAgent-JDGenie：GAIA技术报告

Jiarun Liu, Shiyue Xu, Shangkun Liu, Yang Li, Wen Liu, Min Liu, Xiaoqing Zhou, Hanmin Wang, Shilin Jia, zhen Wang, Shaohua Tian, Hanhao Li, Junbo Zhang, Yongli Yu, Peng Cao, Haofen Wang

Subjects: Computation and Language (cs.CL)

[24] arXiv:2510.00514 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: EuroSpeech: A Multilingual Speech Corpus Show Chinese title

Title: EuroSpeech：多语言语音语料库

Samuel Pfisterer, Florian Grötschla, Luca A. Lanzendörfer, Florian Yan, Roger Wattenhofer

Comments: Published in the 39th Conference on Neural Information Processing Systems (NeurIPS 2025) Track on Datasets and Benchmark

Subjects: Computation and Language (cs.CL) ; Machine Learning (cs.LG)

[25] arXiv:2510.00526 (cross-list from cs.CL) [cn-pdf, pdf, html, other]

Title: Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum Show Chinese title

Title: 超越对数似然：跨模型能力连续体的基于概率的目标函数用于监督微调

Gaotang Li, Ruizhong Qiu, Xiusi Chen, Heng Ji, Hanghang Tong

Comments: 23 pages, 4 figures

Subjects: Computation and Language (cs.CL) ; Machine Learning (cs.LG)