English
Related papers

Related papers: Dynosaur: A Dynamic Growth Paradigm for Instructio…

200 papers

Large vision language models (LVLMs) have demonstrated impressive performance across a wide range of tasks. These capabilities largely stem from visual instruction tuning, which fine-tunes models on datasets consisting of curated…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Myeongkyun Kang , Soopil Kim , Xiaoxiao Li , Sang Hyun Park

Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation…

Computation and Language · Computer Science 2024-02-01 Yushi Bai , Xin Lv , Jiajie Zhang , Yuze He , Ji Qi , Lei Hou , Jie Tang , Yuxiao Dong , Juanzi Li

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Computation and Language · Computer Science 2024-12-23 Barry Menglong Yao , Qifan Wang , Lifu Huang

Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses. However, no studies have shown that instruction-tuning actually teaches LLMs…

Computation and Language · Computer Science 2024-08-12 Khai Loong Aw , Syrielle Montariol , Badr AlKhamissi , Martin Schrimpf , Antoine Bosselut

We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model (e.g.,…

Computation and Language · Computer Science 2023-10-11 Zekun Li , Baolin Peng , Pengcheng He , Michel Galley , Jianfeng Gao , Xifeng Yan

Recently, there has been a growing interest in studying how to construct better code instruction tuning data. However, we observe Code models trained with these datasets exhibit high performance on HumanEval but perform worse on other…

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

Computation and Language · Computer Science 2025-03-21 Ishika Agarwal , Krishnateja Killamsetty , Lucian Popa , Marina Danilevksy

We introduce Instruct-SkillMix, an automated approach for creating diverse, high quality SFT data for instruction-following. The pipeline involves two stages, each leveraging an existing powerful LLM: (1) Skill extraction: uses the LLM to…

Machine Learning · Computer Science 2025-07-08 Simran Kaur , Simon Park , Anirudh Goyal , Sanjeev Arora

With the rapid scaling of large language models (LLMs), structured pruning has become a widely used technique to learn efficient, smaller models from larger ones, delivering superior performance compared to training similarly sized models…

Computation and Language · Computer Science 2025-06-04 Bairu Hou , Qibin Chen , Jianyu Wang , Guoli Yin , Chong Wang , Nan Du , Ruoming Pang , Shiyu Chang , Tao Lei

Charts provide visual representations of data and are widely used for analyzing information, addressing queries, and conveying insights to others. Various chart-related downstream tasks have emerged recently, such as question-answering and…

Computation and Language · Computer Science 2024-03-15 Ahmed Masry , Mehrad Shahmohammadi , Md Rizwan Parvez , Enamul Hoque , Shafiq Joty

Existing methods to fine-tune LLMs, like Adapter, Prefix-tuning, and LoRA, which introduce extra modules or additional input sequences to inject new skills or knowledge, may compromise the innate abilities of LLMs. In this paper, we propose…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Bo Zou , Chao Yang , Yu Qiao , Chengbin Quan , Youjian Zhao

Retrieval-Augmented Generation (RAG) has emerged as a key paradigm for enhancing large language models (LLMs) by incorporating external knowledge. However, current RAG methods face two limitations: (1) they only cover limited RAG scenarios.…

Computation and Language · Computer Science 2025-01-03 Wanlong Liu , Junying Chen , Ke Ji , Li Zhou , Wenyu Chen , Benyou Wang

Visual instruction datasets from various distributors are released at different times and often contain a significant number of semantically redundant text-image pairs, depending on their task compositions (i.e., skills) or reference…

Machine Learning · Computer Science 2025-03-25 Adyasha Maharana , Jaehong Yoon , Tianlong Chen , Mohit Bansal

Effective text generation and chat interfaces for low-resource languages (LRLs) remain a challenge for state-of-the-art large language models (LLMs) to support. This is mainly due to the difficulty of curating high-quality instruction…

Machine Learning · Computer Science 2026-02-09 Mamadou K. Keita , Sebastien Diarra , Christopher Homan , Seydou Diallo

Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational…

Computation and Language · Computer Science 2025-06-03 Shaobo Wang , Xiangqi Jin , Ziming Wang , Jize Wang , Jiajun Zhang , Kaixin Li , Zichen Wen , Zhong Li , Conghui He , Xuming Hu , Linfeng Zhang

Large language models (LLMs) have emerged as powerful tools in natural language processing (NLP), showing a promising future of artificial generated intelligence (AGI). Despite their notable performance in the general domain, LLMs have…

Computation and Language · Computer Science 2025-01-23 Jingyuan Chen , Tao Wu , Wei Ji , Fei Wu

Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…

Cryptography and Security · Computer Science 2023-10-31 Manli Shu , Jiongxiao Wang , Chen Zhu , Jonas Geiping , Chaowei Xiao , Tom Goldstein

Large Language Models (LLMs) have demonstrated remarkable progress through preference-based fine-tuning, which critically depends on the quality of the underlying training data. While human feedback is essential for improving data quality,…

Artificial Intelligence · Computer Science 2025-10-31 Derin Cayir , Renjie Tao , Rashi Rungta , Kai Sun , Sean Chen , Haidar Khan , Minseok Kim , Julia Reinspach , Yue Liu

Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves…

Computation and Language · Computer Science 2023-10-24 Zihan Zhang , Meng Fang , Ling Chen , Mohammad-Reza Namazi-Rad

Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were…

Computation and Language · Computer Science 2025-06-05 Jarvis Guo , Tuney Zheng , Yuelin Bai , Bo Li , Yubo Wang , King Zhu , Yizhi Li , Graham Neubig , Wenhu Chen , Xiang Yue