语言大模型 / LLM

Adapting Mental Health Prediction Tasks for Cross-lingual Learning via Meta-Training and In-context Learning with Large Language Model

Zita Lifelo, Huansheng Ning, Sahraoui Dhelim

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

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models

Haotian Zhang, Haoxuan You, Philipp Dufter, Bowen Zhang, Chen Chen, Hong-You Chen, Tsu-Jui Fu, William Yang Wang, Shih-Fu Chang, Zhe Gan, Yinfei Yang

专题命中 指令微调 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；instruction tuning(abstract)

Comments Preprint. 14 pages, 4 figures

DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model

Chao Gao, Sai Qian Zhang

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

From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning

Xuansheng Wu, Wenlin Yao, Jianshu Chen, Xiaoman Pan, Xiaoyang Wang, Ninghao Liu, Dong Yu

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

Comments Accepted by NAACL 2024

X-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large Language Models with Applications in Protein Mechanics and Molecular Design

Eric L. Buehler, Markus J. Buehler

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

Harnessing Large Language Models for Text-Rich Sequential Recommendation

Zhi Zheng, Wenshuo Chao, Zhaopeng Qiu, Hengshu Zhu, Hui Xiong

专题命中 指令微调 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；SFT(abstract)

Soft-prompt Tuning for Large Language Models to Evaluate Bias

Jacob-Junqi Tian, David Emerson, Sevil Zanjani Miyandoab, Deval Pandya, Laleh Seyyed-Kalantari, Faiza Khan Khattak

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

Large Language Model based Long-tail Query Rewriting in Taobao Search

Wenjun Peng, Guiyang Li, Yue Jiang, Zilong Wang, Dan Ou, Xiaoyi Zeng, Derong Xu, Tong Xu, Enhong Chen

专题命中 指令微调 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；SFT(abstract)

Comments WWW Industry

Knowledge-Augmented Large Language Models for Personalized Contextual Query Suggestion

Jinheon Baek, Nirupama Chandrasekaran, Silviu Cucerzan, Allen herring, Sujay Kumar Jauhar

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

Comments The Web Conference (WWW) 2024

PAL: Proxy-Guided Black-Box Attack on Large Language Models

Chawin Sitawarin, Norman Mu, David Wagner, Alexandre Araujo

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

Nevermind: Instruction Override and Moderation in Large Language Models

Edward Kim

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

Comments 11 pages

Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion

Jinhan Wang, Long Chen, Aparna Khare, Anirudh Raju, Pranav Dheram, Di He, Minhua Wu, Andreas Stolcke, Venkatesh Ravichandran

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

Comments To appear in IEEE ICASSP 2024

DrugAssist: A Large Language Model for Molecule Optimization

Geyan Ye, Xibao Cai, Houtim Lai, Xing Wang, Junhong Huang, Longyue Wang, Wei Liu, Xiangxiang Zeng

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

Comments Geyan Ye and Xibao Cai are equal contributors; Longyue Wang is corresponding author

Machine Translation with Large Language Models: Prompt Engineering for Persian, English, and Russian Directions

Nooshin Pourkamali, Shler Ebrahim Sharifi

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

Comments 34 pages, 46 figures

Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models

Zhou Ziheng, Yingnian Wu, Song-Chun Zhu, Demetri Terzopoulos

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

Comments 81 pages, 77 figures

To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning

Junke Wang, Lingchen Meng, Zejia Weng, Bo He, Zuxuan Wu, Yu-Gang Jiang

专题命中 指令微调 ：instruction tuning(title,abstract)；prompting(title,abstract)；large language model(abstract)；language model(abstract)

Comments techical report; work in progress

LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

Yixiao Li, Yifan Yu, Chen Liang, Pengcheng He, Nikos Karampatziakis, Weizhu Chen, Tuo Zhao

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

Long-Form Speech Translation through Segmentation with Finite-State Decoding Constraints on Large Language Models

Arya D. McCarthy, Hao Zhang, Shankar Kumar, Felix Stahlberg, Ke Wu

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

Comments accepted to the Findings of EMNLP 2023. arXiv admin note: text overlap with arXiv:2212.09895

LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model

Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal, Raphael Olivier, Ankit Shah, Joseph Konan, Dareen Alharthi, Hazim T Bukhari, Massa Baali, Soham Deshmukh, Michael Kuhlmann, Bhiksha Raj, Rita Singh

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

Analysis of Disinformation and Fake News Detection Using Fine-Tuned Large Language Model

Bohdan M. Pavlyshenko

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

INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation

Yuji Chai, John Gkountouras, Glenn G. Ko, David Brooks, Gu-Yeon Wei

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

Learning from Generalization Patterns: An Evaluation-Driven Approach to Enhanced Data Augmentation for Fine-Tuning Small Language Models

Huan Song, Deeksha Razdan, Yiyue Qian, Arijit Ghosh Chowdhury, Parth Patwa, Aman Chadha, Shinan Zhang, Sharlina Keshava, Hannah Marlowe

机构 * AWS Generative AI Innovation Center（AWS生成式AI创新中心） 纠错

专题命中 指令微调 ：language model(title,abstract)；small language model(title,abstract)；LLM(abstract,comments)；分类 cs.AI、cs.LG

Comments Neural Information Processing Systems (NeurIPS 2025) Workshop: Evaluating the Evolving LLM Lifecycle

Modeling Layered Consciousness with Multi-Agent Large Language Models

Sang Hun Kim, Jongmin Lee, Dongkyu Park, So Young Lee, Yosep Chong

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

Comments 20 pages, 4 figures, accepted for presentation at EMNLP 2025 Workshop on Active and Passive LLM Personalization (PALS) OpenReview: https://openreview.net/forum?id=rUtNkYvGJI

Index SLM Technical Report

索引SLM技术报告

Tianjiao Li, Lusheng Zhang, Shien He, Xiaojing Liu, Tianxing Yan, Mengran Yu, Ziang Cui, Kai Zhao, Xipeng Wang, Yang Liu, Yuxin Li

机构 * Bilibili（哔哩哔哩） 纠错

专题命中 指令微调 ：SLM(title,title_cn)；language model(abstract)；foundation model(abstract)；small language model(abstract)

AI总结 哔哩哔哩开发Index-1.9B系列小语言模型，包括基础模型等四个模型。预训练采用特定方法，Index-1.9B-Base在标准基准测试表现出色，还进行了多项控制研究，所有模型及评估代码已公开。

Comments 16 pages, 9 figures. v3: updated author list to add Xipeng Wang

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

TRCA：面向长 horizon 大语言模型智能体的逐步规则信用分配

Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv, Heng Chang, Sen Cui, Faguo Wu, Shiji Zhou

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

AI总结 针对长 horizon LLM 智能体稀疏最终结果优化导致的细粒度信用分配难题，提出无需学习评估器或成功锚点的 TRCA，在多基准上取得显著性能提升。

Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning

通过质量感知偏好学习增强大语言模型生成代码的非功能质量合规性

Liang Lu, Yuan Jiang, Christoph Treude, Shuzheng Gao, Jingyu Xiao, Xiaohong Su, Michael R. Lyu

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

AI总结 针对LLM生成代码存在的非功能质量合规性问题，提出质量感知偏好学习框架，通过三阶段方法提升代码合规性，在保持功能正确的同时实现显著性能提升，具备良好实用价值。

EmoS: A Theory-Grounded Framework for Evaluating and Aligning Emotional Intelligence in Spoken Language Models

EmoS：用于评估和对齐口语语言模型中情商的基于理论的框架

Junyu Wang, Siyuan Zhang, Peiyuan Jiang, Jian Zong, Jingyu Zhang, Tianrui Wang, Yuqin Lin, Zhenghui Chen, Shuqing Xie, Ziyang Ma, Meng Ge, Xiaobao Wang, Longbiao Wang, Jianwu Dang

专题命中 指令微调 ：SFT(summary_cn,abstract)；language model(title,abstract)；SLM(abstract_cn)；分类 cs.CL

AI总结 本研究针对口语语言模型情商评估缺乏理论框架的问题，构建了EmoSBench基准，开发了基于SFT和GRPO优化的EmoS评估模型，其在EmoSBench上准确率达83.8%，接近人类水平。

Comments Accepted at ACM Multimedia 2026 (MM '26)

UNSPECIFIC: General Constraint Synthesis for Breaking Copy-and-Paste Shortcut in LLM Instruction Following

UNSPECIFIC：用于破解大语言模型指令遵循中复制粘贴捷径的通用约束合成方法

Jeet Sharma, Balpreet Kaur, Jeremiah Hong, Hamed Zamani, Haw-Shiuan Chang

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

AI总结 本研究针对LLM指令遵循中复制粘贴的捷径问题，提出UNSPECIFIC框架，通过合成共有的约束、强化易满足约束、在文章及其摘要上评估来破解该问题，构建基准并验证其有效性。

Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification

面向黑盒大语言模型所有权验证的针对性反事实指纹技术

Yutong Wu, Xiaofan Bai, Shixin Li, Pingyi Hu, Ziqi Zhou, Zilong Wang, Xiaojing Ma, Songfeng Lu, Yuhong Li, Jin Xuan, Yi Wang, Dongmei Zhang, Bin Benjamin Zhu

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

AI总结 针对黑盒LLM所有权验证的挑战，提出TCF框架，将开放式生成对比转化为受限答案的反事实迁移，在四个LLM系列上平均AUC达0.9861，优于TRAP等现有方法。

Comments 37 pages, 18 figures, 23 tables

Training-Free Token-Level Steering for LLM Personalized Co-Writing

面向LLM个性化协同写作的无训练令牌级引导

Wenhao Mao, Chengbin Hou, Weixiao Wang, Jialiang Zhu, Min Liu, Yibin Hao, Hairong Lv

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

AI总结 针对LLM个性化协同写作的需求，提出无训练框架SteerWrite，无需梯度更新即可适配专业领域，在多数据集、指标和模型上实现SOTA性能，大幅降低人工编辑工作量。