arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

共收录 12193 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12193 篇

2511.20987 2025-11-27 math.CO cs.AI cs.LG cs.NE 79%

Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction

即使有AI,双射发现仍然困难:OpenEvolve在新型双射构造中的机遇与挑战

Davis Brown, Jesse He, Helen Jenne, Henry Kvinge, Max Vargas

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

AI总结 本文探讨了OpenEvolve在双射构造中的应用,发现尽管AI有潜力,但寻找新颖双射仍具挑战性,需人类数学家参与。

Comments 16 pages, 3 figures. This is an extended abstract submitted to FPSAC 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20120 2025-11-26 cs.CL cs.AI 79%

"When Data is Scarce, Prompt Smarter"... Approaches to Grammatical Error Correction in Low-Resource Settings

当数据稀缺时,提示更聪明...在低资源环境下进行语法错误纠正的方法

Somsubhra De, Harsh Kumar, Arun Prakash A

机构 * IIT Madras(印度理工学院马德拉斯学院) AI4Bharat

专题命中 其他LLM :large language model(abstract);language model(abstract);prompting(abstract);分类 cs.CL、cs.AI

AI总结 本研究通过提示方法和少量样本策略,利用大型语言模型在低资源印地语系语言中实现高效语法错误纠正,取得领先成果。

Comments 10 pages, 5 figures, 5 tables; Accept-demonstration at BHASHA Workshop, IJCNLP-AACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13013 2025-11-26 cs.CL cs.AI 79%

Missing the human touch? A computational stylometry analysis of GPT-4 translations of online Chinese literature

缺少人文关怀?对GPT-4翻译在线中文文学的计算风格分析

Xiaofang Yao, Yong-Bin Kang, Anthony McCosker

机构 * The University of Hong Kong(香港大学) Swinburne University of Technology(斯威本科技大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

AI总结 本研究通过计算风格分析,发现GPT-4在中文文学翻译中能复现人类翻译的风格特征,表明大型语言模型可能在文学翻译中再现'人文关怀'。

Comments 15 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11667 2025-11-25 cs.LG cs.AI 79%

Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion

超越表面遗忘:通过知识密度估计和块重新插入实现彻底遗忘

Feng Guo, Yuntao Wen, Shen Gao, Junshuo Zhang, Shuo Shang

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

AI总结 KUnBR通过知识密度估计和块重新插入策略,有效解决大语言模型中有害知识的彻底移除问题,实现高效的遗忘与模型实用性平衡。

Comments Accepted by AAAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.01215 2025-11-25 cs.CL cs.AI cs.PL cs.SE 79%

From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging

从代码到正确性:通过分层调试关闭代码生成的最后一公里

Yuling Shi, Songsong Wang, Chengcheng Wan, Min Wang, Xiaodong Gu

机构 * Shanghai Jiao Tong University(上海交通大学) University of California, Davis(加州大学戴维斯分校) East China Normal University(华东师范大学) University of Pennsylvania(宾夕法尼亚大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

AI总结 本文提出MGDebugger,一种分层调试器,通过多粒度分析提升代码生成的准确性与修复效率。

Comments Accepted to ICSE 2026. Code and data available at https://github.com/YerbaPage/MGDebugger

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.10653 2025-11-17 cs.CL cs.AI quant-ph 79%

Hybrid Quantum Transformer for Language Generation

Desheng Kong, Xiangshuo Cui, Jiaying Jin, Jing Xu, Donglin Wang

机构 * Nankai University(南开大学) Beijing Sursen Information Technology Co., Ltd(北京搜森信息技术有限公司)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06826 2025-11-11 cs.CL cs.AI 79%

Beyond Plain Demos: A Demo-centric Anchoring Paradigm for In-Context Learning in Alzheimer's Disease Detection

Puzhen Su, Haoran Yin, Yongzhu Miao, Jintao Tang, Shasha Li, Ting Wang

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

Comments Accepted to the 40th Annual AAAI Conference on Artificial Intelligence (2026) - Main Technical Track (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04697 2025-11-10 cs.SI cs.AI cs.CL 79%

Simulating Misinformation Vulnerabilities With Agent Personas

David Farr, Lynnette Hui Xian Ng, Stephen Prochaska, Iain J. Cruickshank, Jevin West

机构 * School of Information Science University of Washington(信息科学学院华盛顿大学) School of Computer Science Carnegie Mellon University(计算机科学学院卡内基梅隆大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

Comments Accepted to Winter Simulation Conference 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.18469 2025-11-10 cs.CL cs.LG 79%

Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities

Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG

Comments Accepted to NAACL 2025 Main (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.00198 2025-11-04 cs.CL cs.AI 79%

Training LLMs Beyond Next Token Prediction -- Filling the Mutual Information Gap

Chun-Hao Yang, Bo-Han Feng, Tzu-Yuan Lai, Yan Yu Chen, Yin-Kai Dean Huang, Shou-De Lin

机构 * National Taiwan University(国立台湾大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03665 2025-11-04 cs.LG cs.AI 79%

A DbC Inspired Neurosymbolic Layer for Trustworthy Agent Design

Claudiu Leoveanu-Condrei

机构 * ExtensityAI

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

Comments 4 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.11390 2025-10-29 cs.CL cs.LG 79%

Says Who? Effective Zero-Shot Annotation of Focalization

Rebecca M. M. Hicke, Yuri Bizzoni, Pascale Feldkamp, Ross Deans Kristensen-McLachlan

机构 * Department of Computer Science, Cornell University(计算机科学系,康奈尔大学) Center for Humanities Computing, Aarhus University(人文学计算中心,奥胡斯大学) Department of Linguistics, Cognitive Science, and Semiotics, Aarhus University(语言学、认知科学与符号学系,奥胡斯大学) TEXT - Center for the Contemporary Cultures of Text, Aarhus University(文本当代文化中心,奥胡斯大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG

Comments Accepted at CHR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.10372 2025-10-28 cs.AI cs.CL cs.CY cs.GT 79%

Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulation

Qiliang Chen, Sepehr Ilami, Nunzio Lore, Babak Heydari

机构 * Department of Mechanical and Industrial Engineering(机械与工业工程系) Institute of Experiential AI(体验人工智能研究所) Network Science Institute(网络科学研究所) Northeastern University(东北大学) Boston, MA 02115, United States(波士顿,马萨诸塞州,02115,美国)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21983 2025-10-28 cs.CL cs.AI 79%

Uncovering the Persuasive Fingerprint of LLMs in Jailbreaking Attacks

Havva Alizadeh Noughabi, Julien Serbanescu, Fattane Zarrinkalam, Ali Dehghantanha

机构 * Cyber Science Lab, University of Guelph(圭尔夫大学网络安全实验室) College of Engineering, University of Guelph(圭尔夫大学工程学院)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20612 2025-10-24 cs.CY cs.AI cs.CR cs.LG econ.GN q-fin.EC 79%

Black Box Absorption: LLMs Undermining Innovative Ideas

Wenjun Cao

机构 * Independent Researcher(独立研究者)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20187 2025-10-24 cs.LG cs.CL 79%

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

Dian Yu, Yulai Zhao, Kishan Panaganti, Linfeng Song, Haitao Mi, Dong Yu

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG

Comments 15 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01002 2025-10-24 cs.CL cs.AI 79%

Token embeddings violate the manifold hypothesis

Michael Robinson, Sourya Dey, Tony Chiang

机构 * Mathematics and Statistics(数学与统计学) American University(美国大学) Galois, Inc.(Galois公司) Department of Mathematics, University of Washington(华盛顿大学数学系)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

Comments 30 pages, 9 figures, 10 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.14456 2025-10-22 cs.CL cs.AI 79%

Correct-Detect: Balancing Performance and Ambiguity Through the Lens of Coreference Resolution in LLMs

Amber Shore, Russell Scheinberg, Ameeta Agrawal, So Young Lee

机构 * Portland State University(波特兰州立大学) Miami University(迈阿密大学)

专题命中 其他LLM :large language model(abstract);language model(abstract);prompting(abstract);分类 cs.CL、cs.AI

Comments Accepted at EMNLP 2025 (main)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.19398 2025-10-22 cs.AI cs.GT cs.LG 79%

Do LLMs Strategically Reveal, Conceal, and Infer Information? A Theoretical and Empirical Analysis in The Chameleon Game

Mustafa O. Karabag, Jan Sobotka, Ufuk Topcu

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.17000 2025-10-21 cs.CR cs.CL cs.LG 79%

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs

Masahiro Kaneko, Timothy Baldwin

机构 * MBZUAI Abu Dhabi, UAE(阿布扎赫德MBZUAI)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG

Comments NeurIPS 2025 (spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03567 2025-10-17 cs.LG cs.CL cs.CR cs.CY math.OC 79%

Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs

Fatmazohra Rezkellah, Ramzi Dakhmouche

机构 * Department of Computer Science, Université Paris-Dauphine(巴黎-索邦大学计算机科学系) Institute of Mathematics, EPFL(苏黎世联邦理工学院数学研究所) Computational Engineering Lab, Empa(Empa计算工程实验室)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14312 2025-10-17 cs.AI cs.CL cs.CR 79%

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies

Mason Nakamura, Abhinav Kumar, Saaduddin Mahmud, Sahar Abdelnabi, Shlomo Zilberstein, Eugene Bagdasarian

机构 * University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校) ELLIS Institute(ELLIS研究所) MPI for Intelligent Systems(智能系统研究所) Tübingen AI Center(图宾根人工智能中心)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13811 2025-10-17 cs.HC cs.AI cs.CL 79%

Generative AI in Heritage Practice: Improving the Accessibility of Heritage Guidance

Jessica Witte, Edmund Lee, Lisa Brausem, Verity Shillabeer, Chiara Bonacchi

机构 * Edinburgh Futures Institute(爱丁堡未来研究所) University of Edinburgh(爱丁堡大学) Historic England(英国历史遗产委员会) School of History, Classics & Archaeology University of Edinburgh(历史、古典学与考古学学院爱丁堡大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

Comments 21 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02016 2025-10-09 cs.CL cs.AI 79%

Mind the (Belief) Gap: Group Identity in the World of LLMs

Angana Borah, Marwa Houalla, Rada Mihalcea

机构 * University of Michigan - Ann Arbor(密歇根大学安阿伯分校)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

Comments Accepted to ACL 2025 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.00276 2025-10-02 cs.CL cs.LG 79%

SafePassage: High-Fidelity Information Extraction with Black Box LLMs

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

机构 * Pattern Data

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.20485 2025-10-02 cs.CR cs.CL cs.LG 79%

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation

Harsh Chaudhari, Giorgio Severi, John Abascal, Anshuman Suri, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea

机构 * Northeastern University(东北大学) OpenAI

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24090 2025-09-30 cs.CL cs.AI 79%

Large-Scale Constraint Generation -- Can LLMs Parse Hundreds of Constraints?

Matteo Boffa, Jiaxuan You

机构 * Politecnico di Torino(托斯大学) University of Urbana Champaign (UIUC)(乌尔班纳-香槟大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.19301 2025-09-30 cs.CL cs.AI 79%

Beyond checkmate: exploring the creative chokepoints in AI text

Nafis Irtiza Tripto, Saranya Venkatraman, Mahjabin Nahar, Dongwon Lee

机构 * The Pennsylvania State University(宾夕法尼亚州立大学) Amazon(亚马逊公司)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

Comments Accepted at 30th Conference on Empirical Methods in Natural Language Processing (EMNLP'25 Main conference). 9 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18244 2025-09-30 cs.LG cs.AI 79%

Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data

Chu-Cheng Lin, Daiyi Peng, Yifeng Lu, Ming Zhang, Eugene Ie

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.20021 2025-09-30 cs.RO cs.AI cs.LG 79%

When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation

Matin Aghaei, Lingfeng Zhang, Mohammad Ali Alomrani, Mahdi Biparva, Yingxue Zhang

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

Comments Preprint; under peer review

详情

展开后加载摘要…

URL PDF HTML 收藏