语言大模型 / LLM

Mission: Impossible Language Models

Julie Kallini, Isabel Papadimitriou, Richard Futrell, Kyle Mahowald, Christopher Potts

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

Was it Slander? Towards Exact Inversion of Generative Language Models

Adrians Skapars, Edoardo Manino, Youcheng Sun, Lucas C. Cordeiro

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

Comments 4 pages, 3 figures

Language Models as Zero-Shot Trajectory Generators

Teyun Kwon, Norman Di Palo, Edward Johns

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

Comments Published in IEEE Robotics and Automation Letters (Volume: 9, Issue: 7, July 2024, Pages: 6728-6735); 10 pages, 12 figures

Journal ref IEEE Robotics and Automation Letters (Volume: 9, Issue: 7, July 2024, Pages: 6728-6735)

DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection

Xiao Yu, Yuang Qi, Kejiang Chen, Guoqiang Chen, Xi Yang, Pengyuan Zhu, Xiuwei Shang, Weiming Zhang, Nenghai Yu

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

Why Larger Language Models Do In-context Learning Differently?

Zhenmei Shi, Junyi Wei, Zhuoyan Xu, Yingyu Liang

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

Instruction-tuned Language Models are Better Knowledge Learners

Zhengbao Jiang, Zhiqing Sun, Weijia Shi, Pedro Rodriguez, Chunting Zhou, Graham Neubig, Xi Victoria Lin, Wen-tau Yih, Srinivasan Iyer

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

Comments ACL 2024. The reproduced data for this paper is available at https://github.com/Edward-Sun/PIT

Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Zeming Wei, Yifei Wang, Ang Li, Yichuan Mo, Yisen Wang

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

Self-HWDebug: Automation of LLM Self-Instructing for Hardware Security Verification

Mohammad Akyash, Hadi Mardani Kamali

专题命中 其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Frozen Transformers in Language Models Are Effective Visual Encoder Layers

Ziqi Pang, Ziyang Xie, Yunze Man, Yu-Xiong Wang

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

Comments ICLR 2024 Spotlight. 23 pages, 13 figures. Code at https://github.com/ziqipang/LM4VisualEncoding

OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models

Fuzhao Xue, Zian Zheng, Yao Fu, Jinjie Ni, Zangwei Zheng, Wangchunshu Zhou, Yang You

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

CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM

Chengyue Yu, Lei Zang, Jiaotuan Wang, Chenyi Zhuang, Jinjie Gu

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

Language Models Represent Space and Time

Wes Gurnee, Max Tegmark

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

How Multimodal Integration Boost the Performance of LLM for Optimization: Case Study on Capacitated Vehicle Routing Problems

Yuxiao Huang, Wenjie Zhang, Liang Feng, Xingyu Wu, Kay Chen Tan

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

Comments 8pages,3 figures, 2 tables

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, Jifeng Dai

专题命中 其他LLM ：foundation model(title,abstract)；LLM(abstract)；large language model(abstract)；language model(abstract)

Comments 25 pages, 5 figures, 28 tables

Detecting Language Model Attacks with Perplexity

Gabriel Alon, Michael Kamfonas

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

The Internal State of an LLM Knows When It's Lying

Amos Azaria, Tom Mitchell

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

HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models

Swaroop Mishra, Elnaz Nouri

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

Comments ACL 2023 Findings

Prompt Sapper: LLM-Empowered Software Engineering Infrastructure for AI-Native Services

Zhenchang Xing, Qing Huang, Yu Cheng, Liming Zhu, Qinghua Lu, Xiwei Xu

专题命中 其他LLM ：LLM(title,abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Systematic Rectification of Language Models via Dead-end Analysis

Meng Cao, Mehdi Fatemi, Jackie Chi Kit Cheung, Samira Shabanian

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

Comments The Eleventh International Conference on Learning Representations, ICLR'23

Journal ref ICLR 2023

Inaccessible Neural Language Models Could Reinvigorate Linguistic Nativism

Patrick Perrine

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

Comments 6 pages

LLM-grounded Video Diffusion Models

Long Lian, Baifeng Shi, Adam Yala, Trevor Darrell, Boyi Li

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

Comments ICLR 2024. Project Page: https://llm-grounded-video-diffusion.github.io/

Local AI pre-screening for human triple-blind peer review in health sciences

健康科学领域中用于人类三重盲同行评审的本地AI预筛选

Rodrigo Martins Boos

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

AI总结 该研究针对健康科学领域同行评审的AI滥用问题，提出三重盲多LLM本地预筛选框架，保留人类最终裁决权，可减少评审延迟且更透明合规。

Comments 16 pages, 1 figure

MDB-Link: Hierarchical Schema Linking for Multi-Database Text-to-SQL

MDB-Link：面向多数据库Text-to-SQL的分层模式链接方法

Beiyu Xu, Zhenyu Wu, Jiaoyan Chen, Riza theresa Batista-navarro

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

AI总结 本文针对多数据库Text-to-SQL场景提出分层模式链接框架MDB-Link，结合LLM实现数据库定位与列选择，在多个数据集上性能及运行速度均优于基线方法，可高效支撑SQL生成。

Directed Neuro-Symbolic Stochastic Execution for Verification of Distributed Parallel AI Programs

用于分布式并行AI程序验证的定向神经符号随机执行

Gautham Koorma, Vikas Sharma, George Edwards, Mahdi Eslamimehr

机构 * Quandary Peak Research（昆达里峰研究院） 纠错

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

AI总结 针对分布式并行AI程序的可靠性缺口，提出DNSSE混合测试框架，结合LLM调度预测与符号约束求解等，实现更优的并发bug检测率与分支覆盖率。

Comments 1 Figure, 1 Algorithm, 1 Figure, 2 Tables

QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction

QuanTiMedAI：由智能体人工智能引导的量子增强时间序列模型用于心脏骤停死亡率预测

Mutasim Fuad Sarker, Adiba Rahman Namira, Wafa Binte Alam, Md Adnan Arefeen, Mahzabeen Emu, Sumaiya Tabassum Nimi

机构 * North South University（北南大学） ； Memorial University（纪念大学） 纠错

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

AI总结 该研究针对心脏骤停死亡率预测的静态数据局限，提出QuanTiMedAI量子-智能体框架，结合智能体LLM与量子循环网络，在MIMIC-IV数据集上仅用605个参数实现0.852的AUROC，优于现有最先进基线。

Comments Submitted for review

Where Models Converge and Humans Diverge: A Coverage Framework for Distributional Pluralism in Open-Ended Generation

模型收敛与人类分歧：开放式生成中分布多元性的覆盖框架

Zini Yang, Emily Wenger, Richard So

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

AI总结 本文针对LLM与人类写作间的分布差距问题，提出以人类写作经验分布为基准的框架，通过LLM-Cov和IBR指标测量LLM生成内容的分布广度，发现当前LLM内容合理但狭窄，可用于评估其“文化覆盖范围”。

Comments 18 pages, 4 figures

GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs

GRIMIP：一种使用LLM进行MIP求解器实例特定配置的通用框架

Yidong Luo, Xuemin Chen, Chenguang Wang, Fangzhou Zhu, Tao Zhong, Tianshu Yu

机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院） ； School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院） 纠错

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

AI总结 提出GRIMIP框架，结合大语言模型的语义推理与贝叶斯优化的高效搜索，为混合整数规划求解器配置超参数，在MIPLIB等基准上实现超过40%的原始对偶积分减少。

AutoFOAM: The Self-Refining Autonomous OpenFOAM Agent

AutoFOAM：自优化自主OpenFOAM智能体

Arun Govind Neelan, A Seshaditya

机构 * SimuNetics ； Onnes Cryogenics ； Quasi AI 纠错

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

AI总结 AutoFOAM是基于Qwen-coder 2.5-14B微调的自主LLM智能体，通过7阶段迭代循环及三种抗退化机制，可基于自然语言指令完成OpenFOAM模拟，助力CFD工作流程普及与快速原型开发。

Specula: Scaling formal specifications for autonomous model checking of system code

Specula：扩展用于系统代码自主模型检查的形式规范

Qian Cheng, Saad Mohammad Rafid Pial, Ruize Tang, Yiming Su, Emilie Ma, Finn Hackett, Ivan Beschastnikh, Yu Huang, Tianyin Xu

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

AI总结 Specula利用大语言模型编码代理为系统代码生成形式规范，通过自我进化循环解决LLM技术局限，实现自主模型检查，应用于48个开源项目发现众多错误，消除形式方法应用障碍，助力系统代码验证。

Comments 17 pages, 11 figures

Human diversity fuels collective creativity that large language models cannot simulate or sustain

人类多样性催生了大型语言模型无法模拟或维持的集体创造力

Mengchen Dong, Hiromu Yakura

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

AI总结 该研究通过实验发现，L2写作者的集体多样性优于L1写作者，AI构思会压缩集体多样性而AI润色可保留，模拟显示AI无法达到人类群体的创意多样性，人机协作设计影响人类多样性的存续。