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

• URL: http://arxiv.org/abs/2310.00492v3
• Date: Thu, 4 Apr 2024 16:30:31 GMT
• Title: From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
• Authors: Xuansheng Wu, Wenlin Yao, Jianshu Chen, Xiaoman Pan, Xiaoyang Wang, Ninghao Liu, Dong Yu,
• Abstract summary: We investigate how instruction tuning adjusts pre-trained models with a focus on intrinsic changes. The impact of instruction tuning is then studied by comparing the explanations derived from the pre-trained and instruction-tuned models. Our findings reveal three significant impacts of instruction tuning.
• Score: 63.63840740526497
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs [4.096028601599825]
  Large Language Models (LLMs) for public use require continuous pre-training to remain up-to-date with the latest data. This study aims to find the most compute-efficient strategy to gain up-to-date knowledge and instruction-following capabilities without requiring any instruction data and fine-tuning.
  arXiv  Detail & Related papers  (2024-10-14T17:20:30Z)
• SwitchCIT: Switching for Continual Instruction Tuning of Large Language Models [14.085371250265224]
  Large language models (LLMs) have exhibited impressive capabilities in various domains, particularly in general language understanding. However these models, trained on massive text data, may not be finely optimized for specific tasks triggered by instructions. This work addresses the catastrophic forgetting in continual instruction learning for LLMs through a switching mechanism for routing computations to parameter-efficient tuned models.
  arXiv  Detail & Related papers  (2024-07-16T14:37:33Z)
• Controllable Navigation Instruction Generation with Chain of Thought Prompting [74.34604350917273]
  We propose C-Instructor, which utilizes the chain-of-thought-style prompt for style-controllable and content-controllable instruction generation. C-Instructor renders generated instructions more accessible to follow and offers greater controllability over the manipulation of landmark objects.
  arXiv  Detail & Related papers  (2024-07-10T07:37:20Z)
• Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning [13.535110749767451]
  We propose a novel continual instruction tuning method based on Key-part Information Gain (KPIG) Our method computes the information gain on masked parts to dynamically replay data and refine the training objective. Experiments demonstrate our method achieves superior performance on both seen and held-out tasks.
  arXiv  Detail & Related papers  (2024-03-15T06:54:20Z)
• Demystifying Instruction Mixing for Fine-tuning Large Language Models [29.69436955342966]
  This study categorizes instructions into three primary types: NLP downstream tasks, coding, and general chat. We find that certain instruction types are more advantageous for specific applications but can negatively impact other areas.
  arXiv  Detail & Related papers  (2023-12-17T18:44:26Z)
• RecExplainer: Aligning Large Language Models for Explaining Recommendation Models [50.74181089742969]
  Large language models (LLMs) have demonstrated remarkable intelligence in understanding, reasoning, and instruction following. This paper presents the initial exploration of using LLMs as surrogate models to explain black-box recommender models. To facilitate an effective alignment, we introduce three methods: behavior alignment, intention alignment, and hybrid alignment.
  arXiv  Detail & Related papers  (2023-11-18T03:05:43Z)
• Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment [15.180715595425864]
  We introduce a novel method to improve the prompt learning of vision-language models by incorporating pre-trained large language models (LLMs) With DuAl-PT, we propose to learn more context-aware prompts, benefiting from both explicit and implicit context modeling. Empirically, DuAl-PT achieves superior performance on 11 downstream datasets on few-shot recognition and base-to-new generalization.
  arXiv  Detail & Related papers  (2023-09-08T06:51:15Z)
• Instruction Position Matters in Sequence Generation with Large Language Models [67.87516654892343]
  Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization. We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
  arXiv  Detail & Related papers  (2023-08-23T12:36:57Z)
• Enhancing Large Language Models Against Inductive Instructions with Dual-critique Prompting [55.15697111170836]
  This paper reveals the behaviors of large language models (LLMs) towards textitinductive instructions and enhance their truthfulness and helpfulness accordingly. After extensive human and automatic evaluations, we uncovered a universal vulnerability among LLMs in processing inductive instructions. We identify that different inductive styles affect the models' ability to identify the same underlying errors, and the complexity of the underlying assumptions also influences the model's performance.
  arXiv  Detail & Related papers  (2023-05-23T06:38:20Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  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 to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.