语言大模型 / LLM

Torque-Aware Momentum

Pranshu Malviya, Goncalo Mordido, Aristide Baratin, Reza Babanezhad Harikandeh, Gintare Karolina Dziugaite, Razvan Pascanu, Sarath Chandar

机构 * Chandar Research Lab（钱达尔研究实验室） ； Mila - Québec AI Institute（米拉 - 魁北克人工智能研究所） ； Polytechnique Montréal（蒙特利尔理工学院） ； Samsung SAIT AI Lab Montréal（三星SAIT人工智能实验室蒙特利尔分部） ； Google DeepMind（谷歌DeepMind） 纠错

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

See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition

Chongjie Si, Xiaokang Yang, Wei Shen

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 指令微调 ：foundation model(abstract)；prompting(abstract)；分类 cs.AI、cs.LG

Comments Codes in https://github.com/Chongjie-Si/Subspace-Tuning

Is Parameter Collision Hindering Continual Learning in LLMs?

Shuo Yang, Kun-Peng Ning, Yu-Yang Liu, Jia-Yu Yao, Yong-Hong Tian, Yi-Bing Song, Li Yuan

机构 * School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院） ； Peng Cheng Laboratory（鹏城实验室） ； DAMO Academy, Alibaba Group（阿里巴巴达摩院） ； Hupan Lab（湖畔实验室） 纠错

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

Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances

Zehui Wu, Ziwei Gong, Lin Ai, Pengyuan Shi, Kaan Donbekci, Julia Hirschberg

机构 * Columbia University（哥伦比亚大学） 纠错

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

Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters

Daniil Gurgurov, Mareike Hartmann, Simon Ostermann

机构 * Saarland University（萨尔大学） ； German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心） 纠错

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

Comments 9 pages, KaLLM workshop

Journal ref 2024.kallm-1.7

Black-box Model Ensembling for Textual and Visual Question Answering via Information Fusion

Yuxi Xia, Kilm Zaporojets, Benjamin Roth

机构 * Faculty of Computer Science, University of Vienna（维也纳大学计算机科学学院） ； UniVie Doctoral School Computer Science, University of Vienna（维也纳大学UniVie计算机科学博士学院） ； Department of Computer Science, Aarhus University（奥胡斯大学计算机科学系） ； Faculty of Philological and Cultural Studies, University of Vienna（维也纳大学语文与文化研究学院） 纠错

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

Comments 15 pages, 6 figures, 9 tables

Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning

Yuti Liu, Shice Liu, Junyuan Gao, Pengtao Jiang, Hao Zhang, Jinwei Chen, Bo Li

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

Comments Accepted by AAAI 2025

Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations

Sayantan Pal, Souvik Das, Rohini K. Srihari

机构 * State University of New York at Buffalo（纽约州立大学布法罗分校） ； Department of Computer Science and Engineering（计算机科学与工程学院） 纠错

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

Comments Accepted in COLING 2025

REBEL: Reinforcement Learning via Regressing Relative Rewards

Zhaolin Gao, Jonathan D. Chang, Wenhao Zhan, Owen Oertell, Gokul Swamy, Kianté Brantley, Thorsten Joachims, J. Andrew Bagnell, Jason D. Lee, Wen Sun

机构 * Cornell University（康奈尔大学） ； Princeton University（普林斯顿大学） ； Carnegie Mellon University（卡内基梅隆大学） ； Harvard University（哈佛大学） ； Aurora Innovation（极光创新公司） 纠错

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

Comments New experimental results on general chat

RAGraph: A General Retrieval-Augmented Graph Learning Framework

Xinke Jiang, Rihong Qiu, Yongxin Xu, Wentao Zhang, Yichen Zhu, Ruizhe Zhang, Yuchen Fang, Xu Chu, Junfeng Zhao, Yasha Wang

机构 * Key Laboratory of High Confidence Software Technologies (Peking University)（高可信软件技术重点实验室（北京大学）） ； School of Computer Science, Peking University（北京大学计算机学院） ； University of Electronic Science and Technology of China（电子科技大学） ； Center on Frontiers of Computing Studies, Peking University（北京大学前沿计算研究中心） ； Big Data Technology Research Center, Nanhu Laboratory, Jiaxing, China（嘉兴南湖实验室大数据技术研究中心） ； Peking University Information Technology Institute, Tianjin Binhai（北京大学信息技术学院（天津滨海）） 纠错

专题命中 指令微调 ：foundation model(abstract)；prompting(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2024

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks

Akshara Prabhakar, Yuanzhi Li, Karthik Narasimhan, Sham Kakade, Eran Malach, Samy Jelassi

机构 * Princeton University（普林斯顿大学） ； Microsoft Research（微软研究院） ； Harvard University（哈佛大学） 纠错

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

Comments COLING 2025 Industry track; 9 pages plus references and appendices

Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning

Omkar Khade, Shruti Jagdale, Abhishek Phaltankar, Gauri Takalikar, Raviraj Joshi

机构 * Pune Institute of Computer Technology（浦那计算机技术学院） ； Indian Institute of Technology Madras（印度马德拉斯理工学院） ； L3Cube Labs（L3Cube实验室） 纠错

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

You can remove GPT2's LayerNorm by fine-tuning

Stefan Heimersheim

机构 * Apollo Research（阿波罗研究公司） 纠错

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

Comments Presented at the Attributing Model Behavior at Scale (ATTRIB) and Interpretable AI: Past, Present, and Future workshops at NeurIPS 2024

vTune: Verifiable Fine-Tuning for LLMs Through Backdooring

Eva Zhang, Arka Pal, Akilesh Potti, Micah Goldblum

机构 * Ritual ； Columbia University（哥伦比亚大学） 纠错

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

Prompt-Efficient Fine-Tuning for GPT-like Deep Models to Reduce Hallucination and to Improve Reproducibility in Scientific Text Generation Using Stochastic Optimisation Techniques

Daniil Sulimov

机构 * Higher School of Economics (HSE)（高等经济大学（HSE）） ； AI for Computational biology (AIC)（计算生物学人工智能研究所（AIC）） 纠错

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

Comments 73 pages, 6 figures

Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series

Vijay Ekambaram, Arindam Jati, Pankaj Dayama, Sumanta Mukherjee, Nam H. Nguyen, Wesley M. Gifford, Chandra Reddy, Jayant Kalagnanam

机构 * IBM Research（IBM研究院） 纠错

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

Comments Accepted at the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification

Sorouralsadat Fatemi, Yuheng Hu, Maryam Mousavi

机构 * University of Illinois at Chicago（伊利诺伊大学芝加哥分校） ； Arizona State University（亚利桑那州立大学） 纠错

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

GenRL: Multimodal-foundation world models for generalization in embodied agents

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Aaron Courville, Sai Rajeswar

机构 * IDLab, Ghent University（IDLab，根特大学） ； VERSES AI Research Lab（VERSES AI研究实验室） ； Mila, University of Montreal（米拉研究所，蒙特利尔大学） ； ServiceNow Research（ServiceNow研究院） 纠错

专题命中 指令微调 ：language model(abstract)；foundation model(abstract)；分类 cs.AI、cs.LG

Comments Presented at NeurIPS 2024

SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning

Yexiao He, Ziyao Wang, Zheyu Shen, Guoheng Sun, Yucong Dai, Yongkai Wu, Hongyi Wang, Ang Li

机构 * University of Maryland（马里兰大学） ； Clemson University（克莱姆森大学） ； Rutgers University（罗格斯大学） 纠错

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

Comments NeurIPS 2024

A Bayesian Approach to Harnessing the Power of LLMs in Authorship Attribution

Zhengmian Hu, Tong Zheng, Heng Huang

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

CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning

Emanuele Frascaroli, Aniello Panariello, Pietro Buzzega, Lorenzo Bonicelli, Angelo Porrello, Simone Calderara

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

Comments 15 pages, 1 figure. Accepted as ORAL at the The 35th British Machine Vision Conference 2024 (BMVC 2024), Glasgow, UK

KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge

Pengcheng Jiang, Lang Cao, Cao Xiao, Parminder Bhatia, Jimeng Sun, Jiawei Han

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

Comments NeurIPS 2024

Fine-Tuning LLMs for Reliable Medical Question-Answering Services

Ali Anaissi, Ali Braytee, Junaid Akram

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

Comments 8 pages, 10 figures, accepted and to be published in the proceedings of 2024 IEEE International Conference on Data Mining Workshops (ICDMW)

AT-MoE: Adaptive Task-planning Mixture of Experts via LoRA Approach

Xurui Li, Juanjuan Yao

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

Exploring Prompt Engineering: A Systematic Review with SWOT Analysis

Aditi Singh, Abul Ehtesham, Gaurav Kumar Gupta, Nikhil Kumar Chatta, Saket Kumar, Tala Talaei Khoei

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

Comments 14 pages, 1 figures

LoraMap: Harnessing the Power of LoRA Connections

Hyeryun Park, Jeongwon Kwak, Dongsuk Jang, Sumin Park, Jinwook Choi

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

Comments 17 pages, 12 figures, 7 tables

LR-SQL: A Supervised Fine-Tuning Method for Text2SQL Tasks under Low-Resource Scenarios

Wen Wuzhenghong, Zhang Yongpan, Pan Su, Sun Yuwei, Lu Pengwei, Ding Cheng

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

Comments 12pages, 4 figures,submitting to a journal

A Recipe For Building a Compliant Real Estate Chatbot

Navid Madani, Anusha Bagalkotkar, Supriya Anand, Gabriel Arnson, Rohini Srihari, Kenneth Joseph

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

FlipGuard: Defending Preference Alignment against Update Regression with Constrained Optimization

Mingye Zhu, Yi Liu, Quan Wang, Junbo Guo, Zhendong Mao

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

Comments Accepted by EMNLP 2024 Main track

Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning

Jian Gu, Aldeida Aleti, Chunyang Chen, Hongyu Zhang

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

Comments under peer-review