语言大模型 / LLM - arXivDaily 专题

2401.17602 2024-02-01 cs.CL 88%

Assertion Detection Large Language Model In-context Learning LoRA Fine-tuning

Yuelyu Ji, Zeshui Yu, Yanshan Wang

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2401.11500 2024-01-23 cs.RO cs.AI cs.SY eess.SY 88%

Integration of Large Language Models in Control of EHD Pumps for Precise Color Synthesis

Yanhong Peng, Ceng Zhang, Chenlong Hu, Zebing Mao

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

2401.03401 2024-01-09 cs.CL 88%

Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition__Taking TOEFL Independent Writing Task for Example

Wei Xia, Shaoguang Mao, Chanjing Zheng

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2305.05189 2023-11-30 cs.CL cs.CV 88%

SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models

Shanshan Zhong, Zhongzhan Huang, Wushao Wen, Jinghui Qin, Liang Lin

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments accepted by ACM MM 2023

2311.13126 2023-11-23 cs.CL 88%

Towards Better Parameter-Efficient Fine-Tuning for Large Language Models: A Position Paper

Chengyu Wang, Junbing Yan, Wei Zhang, Jun Huang

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2311.07418 2023-11-14 cs.CL cs.SD eess.AS 88%

Speech-based Slot Filling using Large Language Models

Guangzhi Sun, Shutong Feng, Dongcheng Jiang, Chao Zhang, Milica Gašić, Philip C. Woodland

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2311.03812 2023-11-08 cs.CL 88%

Conversations in Galician: a Large Language Model for an Underrepresented Language

Eliseo Bao, Anxo Pérez, Javier Parapar

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 5 pages

2310.18347 2023-10-31 cs.CL 88%

PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter

Haoyan Yang, Zhitao Li, Yong Zhang, Jianzong Wang, Ning Cheng, Ming Li, Jing Xiao

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments Accepted by the Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. (EMNLP2023)

2309.11668 2023-10-24 cs.CL 88%

Towards Effective Disambiguation for Machine Translation with Large Language Models

Vivek Iyer, Pinzhen Chen, Alexandra Birch

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments WMT 2023

2310.09223 2023-10-16 cs.CL cs.CY cs.HC 88%

Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation

Eun Cheol Choi, Emilio Ferrara

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2310.08885 2023-10-16 cs.CL 88%

InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems

Willy Chung, Samuel Cahyawijaya, Bryan Wilie, Holy Lovenia, Pascale Fung

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2310.08017 2023-10-13 cs.CL 88%

Harnessing Large Language Models' Empathetic Response Generation Capabilities for Online Mental Health Counselling Support

Siyuan Brandon Loh, Aravind Sesagiri Raamkumar

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments 7 pages, 1 figure

2310.05002 2023-10-10 cs.CL 88%

Self-Knowledge Guided Retrieval Augmentation for Large Language Models

Yile Wang, Peng Li, Maosong Sun, Yang Liu

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2309.09506 2023-09-20 cs.CV cs.CL 88%

LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models

Zecheng Tang, Chenfei Wu, Juntao Li, Nan Duan

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2308.12097 2023-08-24 cs.CL 88%

Instruction Position Matters in Sequence Generation with Large Language Models

Yijin Liu, Xianfeng Zeng, Fandong Meng, Jie Zhou

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments Codes and results are at https://github.com/Adaxry/Post-Instruction/tree/main

2307.16645 2023-08-01 cs.CL 88%

Scaling Sentence Embeddings with Large Language Models

Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, Fuzhen Zhuang

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2306.01857 2023-06-06 cs.CL 88%

Knowledge of cultural moral norms in large language models

Aida Ramezani, Yang Xu

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2306.01475 2023-06-05 cs.IR cs.LG 88%

Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations

Pan Li, Yuyan Wang, Ed H. Chi, Minmin Chen

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.LG

2305.11000 2023-05-22 cs.CL 88%

SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Dong Zhang, Shimin Li, Xin Zhang, Jun Zhan, Pengyu Wang, Yaqian Zhou, Xipeng Qiu

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

Comments work in progress

2301.13294 2023-05-10 cs.CL 88%

Adaptive Machine Translation with Large Language Models

Yasmin Moslem, Rejwanul Haque, John D. Kelleher, Andy Way

专题命中指令微调：language model(title,abstract)；large language model(title)；LLM(abstract)；分类 cs.CL

Comments EAMT 2023 - Research: technical

2304.14456 2023-05-01 cs.CL cs.HC 88%

Framing the News:From Human Perception to Large Language Model Inferences

David Alonso del Barrio, Daniel Gatica-Perez

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2302.03202 2023-02-10 cs.CL 88%

Exploring the Benefits of Training Expert Language Models over Instruction Tuning

Joel Jang, Seungone Kim, Seonghyeon Ye, Doyoung Kim, Lajanugen Logeswaran, Moontae Lee, Kyungjae Lee, Minjoon Seo

专题命中指令微调：language model(title,abstract)；instruction tuning(title,abstract)；分类 cs.CL

2211.12485 2022-11-23 cs.CL 88%

HyperTuning: Toward Adapting Large Language Models without Back-propagation

Jason Phang, Yi Mao, Pengcheng He, Weizhu Chen

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL

2502.01576 2026-06-04 cs.CV 88%

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models

Robust-LLaVA：大规模鲁棒图像编码器对多模态大语言模型的有效性

Hashmat Shadab Malik, Fahad Shamshad, Muzammal Naseer, Karthik Nandakumar, Fahad Khan, Salman Khan

机构 * Mohamed bin Zayed University of AI（Mohamed bin Zayed人工智能大学）； Khalifa University（卡利法大学）； Michigan State University（密歇根州立大学）； Australian National University（澳大利亚国立大学）

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；foundation model(comments)

AI总结本文提出利用大规模对抗预训练的图像分类模型替代CLIP编码器，以增强多模态大语言模型对视觉对抗扰动的鲁棒性，在无需额外对抗训练的情况下，在视觉问答、图像描述和越狱攻击任务中取得显著鲁棒性提升。

Comments Accepted at Trustworthy FMs Workshop Trust Before Use: Building Foundation Models that You Can Trust (ICCVW) 2025

2402.17679 2024-02-28 cs.SE 88%

The Emergence of Large Language Models in Static Analysis: A First Look through Micro-Benchmarks

Ashwin Prasad Shivarpatna Venkatesh, Samkutty Sabu, Amir M. Mir, Sofia Reis, Eric Bodden

专题命中指令微调：large language model(title,abstract)；language model(title,abstract)；foundation model(comments)

Comments To be published in: ICSE FORGE 2024 (AI Foundation Models and Software Engineering)

2606.06087 2026-08-27 cs.CL cs.AI 版本更新 88%

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

LatentSkill: 从上下文文本技能到LLM智能体的权重内隐技能

Aofan Yu, Chenyu Zhou, Tianyi Xu, Zihan Guo, Rong Shan, Zhihui Fu, Jun Wang, Weiwen Liu, Yong Yu, Weinan Zhang, Jianghao Lin

机构 * Shanghai Jiao Tong University（上海交通大学）； Sun Yat-Sen University（中山大学）； Shanghai Innovation Institute（上海创新研究院）； OPPO Research Institute（OPPO研究院）

专题命中指令微调：LLM(title,title_cn)；分类 cs.CL、cs.AI

AI总结提出LatentSkill框架，通过预训练超网络将文本技能转换为即插即用的LoRA适配器，将技能知识存储在权重空间而非上下文空间，从而减少预填充令牌并提升性能。

Comments 10 pages, 4 figures

2608.12374 2026-08-14 cs.CL cs.AI 新提交 88%

Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities

你在跟我讲逻辑吗？评估语言模型的三段论推理能力

Hanna Abi Akl, Fabien Gandon, Catherine Faron, Pierre Monnin

机构 * Université Côte d’Azur（科特阿祖尔大学）； Inria（法国国家信息与自动化研究所）； CNRS（法国国家科学研究中心）； I3S（信息科学与系统实验室）； Data ScienceTech Institute（数据科学技术学院）

专题命中指令微调：language model(title,abstract)；SFT(abstract,abstract_cn)；small language model(abstract)；分类 cs.CL、cs.AI

AI总结该研究通过扩展FOLIO和P-FOLIO数据集，探究不同KR符号对SLMs三段论推理的影响，提出SEF分类法并开源CLGC框架，为提升小型模型推理能力提供了新方法。

Comments Accepted to the International Joint Conference on Rules and Reasoning (RuleML+RR) 2026

2608.09292 2026-08-11 cs.LG cs.CL 新提交 88%

Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents

超越能力边界：用于自进化大语言模型智能体的零阶优化

Bingzhen Liu, Xiaomeng Fan, Yuwei Wu, Zhi Gao, Mingyang Gao, Chuanhao Li, Yunde Jia

机构 * Beijing Institute of Technology（北京理工大学）； Shenzhen MSU-BIT University（深圳北理莫斯科大学）； Alaya Lab（阿莱亚实验室）

专题命中指令微调：LLM(title,summary_cn)；分类 cs.CL、cs.LG

AI总结本文提出零阶自进化框架，通过扰动LLM的LoRA参数形成闭环自进化循环，结合并行扰动推理等机制，在多基准实验中显著提升了LLM智能体在困难样例上的表现。

2608.07693 2026-08-11 cs.CV cs.AI cs.CL 新提交 88%

CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting

CosmosAlign：适配世界基础模型用于生成式交通视频预测

Quang Minh Dinh, Tuan Kiet Doan

机构 * Simon Fraser University（西蒙菲莎大学）； Institut Polytechnique de Paris（巴黎综合理工学院）

专题命中指令微调：foundation model(title,abstract)；LLM(abstract,abstract_cn)；prompting(abstract)；分类 cs.CL、cs.AI

AI总结该研究提出基于Cosmos3-Nano的CosmosAlign框架，通过两阶段LoRA适配与推理优化，在AI City Challenge 2026 Track 5基准中获76.49分排名第一，实现了高质量交通视频预测。

Comments Accepted at ECCVW 2026

2608.04934 2026-08-06 cs.CL cs.LG 新提交 88%

State2State: Environment-Derived Mid-Training for LLM Agents

State2State：面向大语言模型智能体的环境衍生式中间训练

Xuanyu Lei, Yiqi Zhu, Chenliang Li, Kaiming Liu, Peng Li, Ming Yan, Jieping Ye, Ya-Qin Zhang, Yang Liu

机构 * Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）； Institute for AI, Tsinghua University（清华大学人工智能研究院）； Institute of Intelligent Computing, Alibaba Group（阿里巴巴集团智能计算研究院）

专题命中指令微调：LLM(title,summary_cn)；分类 cs.CL、cs.LG

AI总结该研究提出State2State环境衍生式中间训练方法，无需外部任务与监督，可提升LLM智能体性能及学习效率，具备跨环境泛化潜力。

Comments Work in progress

1. 指令微调 11692 篇

Assertion Detection Large Language Model In-context Learning LoRA Fine-tuning

Integration of Large Language Models in Control of EHD Pumps for Precise Color Synthesis

Empirical Study of Large Language Models as Automated Essay Scoring Tools in English Composition__Taking TOEFL Independent Writing Task for Example

SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models

Towards Better Parameter-Efficient Fine-Tuning for Large Language Models: A Position Paper

Speech-based Slot Filling using Large Language Models

Conversations in Galician: a Large Language Model for an Underrepresented Language

PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter

Towards Effective Disambiguation for Machine Translation with Large Language Models

Automated Claim Matching with Large Language Models: Empowering Fact-Checkers in the Fight Against Misinformation

InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems

Harnessing Large Language Models' Empathetic Response Generation Capabilities for Online Mental Health Counselling Support

Self-Knowledge Guided Retrieval Augmentation for Large Language Models

LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models

Instruction Position Matters in Sequence Generation with Large Language Models

Scaling Sentence Embeddings with Large Language Models

Knowledge of cultural moral norms in large language models

Prompt Tuning Large Language Models on Personalized Aspect Extraction for Recommendations

SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities

Adaptive Machine Translation with Large Language Models

Framing the News:From Human Perception to Large Language Model Inferences

Exploring the Benefits of Training Expert Language Models over Instruction Tuning

HyperTuning: Toward Adapting Large Language Models without Back-propagation

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models

The Emergence of Large Language Models in Static Analysis: A First Look through Micro-Benchmarks

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities

Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents

CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting

State2State: Environment-Derived Mid-Training for LLM Agents