Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a focus on intrinsic changes. Specifically, we first develop several local and global explanation methods, including a gradient-based method for input-output attribution, and techniques for interpreting patterns and concepts in self-attention and feed-forward layers. The impact of instruction tuning is then studied by comparing the explanations derived from the pre-trained and instruction-tuned models. This approach provides an internal perspective of the model shifts on a human-comprehensible level. Our findings reveal three significant impacts of instruction tuning: 1) It empowers LLMs to recognize the instruction parts of user prompts, and promotes the response generation constantly conditioned on the instructions. 2) It encourages the self-attention heads to capture more word-word relationships about instruction verbs. 3) It encourages the feed-forward networks to rotate their pre-trained knowledge toward user-oriented tasks. These insights contribute to a more comprehensive understanding of instruction tuning and lay the groundwork for future work that aims at explaining and optimizing LLMs for various applications. Our code and data are publicly available at https://github.com/JacksonWuxs/Interpret_Instruction_Tuning_LLMs.
LongForm: Effective Instruction Tuning with Reverse Instructions
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）
On the Effect of Instruction Tuning Loss on Generalization
Dept. of Electrical Engineering（电气工程系）；Indian Institute of Technology Delhi（印度理工学院德里）；Media and Data Science Research（媒体与数据科学研究）；Adobe Inc., India（Adobe公司，印度）
Instruction tuning enables pretrained language models to perform new tasks from inference-time natural language descriptions. These approaches rely on vast amounts of human supervision in the form of crowdsourced datasets or user interactions. In this work, we introduce Unnatural Instructions: a large dataset of creative and diverse instructions, collected with virtually no human labor. We collect 64,000 examples by prompting a language model with three seed examples of instructions and eliciting a fourth. This set is then expanded by prompting the model to rephrase each instruction, creating …
We study the design decisions of publicly available instruction tuning methods, and break down the development of Flan 2022 (Chung et al., 2022). Through careful ablation studies on the Flan Collection of tasks and methods, we tease apart the effect of design decisions which enable Flan-T5 to outperform prior work by 3-17%+ across evaluation settings. We find task balancing and enrichment techniques are overlooked but critical to effective instruction tuning, and in particular, training with mixed prompt settings (zero-shot, few-shot, and chain-of-thought) actually yields stronger (2%+) perfor…
University of Southern California（南加州大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；The Pennsylvania State University（宾夕法尼亚州立大学）；University of California, Davis（加利福尼亚大学戴维斯分校）
Demystifying Instruction Mixing for Fine-tuning Large Language Models
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；LibrAI；Monash University（莫纳什大学）；University of British Columbia（不列颠哥伦比亚大学）；The University of Melbourne（墨尔本大学）
LLMs can be easily Confused by Instructional Distractions
IPAI, Seoul National University（IPAI，首尔国立大学）；LG AI Research（LG人工智能研究所）；Dept. of ECE, Seoul National University（电子工程系，首尔国立大学）；SNU-LG AI Research Center（SNU-LG人工智能研究所）
SwitchCIT: Switching for Continual Instruction Tuning
Coordinated Science Laboratory（协调科学实验室）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Mathematics（数学系）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
Czech Technical University in Prague（布拉格捷克技术大学）；National Institute of Mental Health in Prague（布拉格国家精神卫生研究所）；The University of Hong Kong（香港大学）；Shenzhen Mental Health Centre（深圳市精神卫生中心）
