Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency

• URL: http://arxiv.org/abs/2409.07045v1
• Date: Wed, 11 Sep 2024 06:27:50 GMT
• Title: Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency
• Authors: Hanyu Zhao, Li Du, Yiming Ju, Chengwei Wu, Tengfei Pan,
• Abstract summary: We investigate interaction and dependency patterns between different categories of instructions to fine-tune large language models (LLMs) Experimental results across different LLMs demonstrate improved performance over strong baselines on widely adopted benchmarks.
• Score: 12.145516262749643
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the availability of various instruction datasets, a pivotal challenge is how to effectively select and integrate these instructions to fine-tune large language models (LLMs). Previous research mainly focuses on selecting individual high-quality instructions. However, these works overlooked the joint interactions and dependencies between different categories of instructions, leading to suboptimal selection strategies. Moreover, the nature of these interaction patterns remains largely unexplored, let alone optimize the instruction set with regard to them. To fill these gaps, in this paper, we: (1) systemically investigate interaction and dependency patterns between different categories of instructions, (2) manage to optimize the instruction set concerning the interaction patterns using a linear programming-based method, and optimize the learning schema of SFT using an instruction dependency taxonomy guided curriculum learning. Experimental results across different LLMs demonstrate improved performance over strong baselines on widely adopted benchmarks.

Related papers

• RAISE: Reinforenced Adaptive Instruction Selection For Large Language Models [48.63476198469349]
  We propose a task-objective-driven instruction selection framework RAISE. RAISE incorporates the entire instruction fine-tuning process into optimization. It selects instruction at each step based on the expected impact of instruction on model performance improvement.
  arXiv  Detail & Related papers  (2025-04-09T21:17:52Z)
• Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs [29.07102440466282]
  We propose a scalable framework designed to automatically construct alignment preferences grounded in instruction fulfillment efficacy. Our method involves an automated preference construction coupled with a dedicated verification process. Experiments conducted on Qwen2VL-7B demonstrate IPA's effectiveness across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-03-26T08:19:02Z)
• MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training [36.483136685734735]
  We propose a Multi-granularity Self-Contrastive Training (MuSC) framework to improve the complex instruction alignment without relying on a stronger model. Our method is evaluated on open-sourced models, and experiment results show our method achieves significant improvement on both complex and general instruction-following benchmarks.
  arXiv  Detail & Related papers  (2025-02-17T08:12:49Z)
• A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
  We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts. With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS) Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements. High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
  arXiv  Detail & Related papers  (2024-12-18T15:38:39Z)
• Towards a Unified View of Preference Learning for Large Language Models: A Survey [88.66719962576005]
  Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. We decompose all the strategies in preference learning into four components: model, data, feedback, and algorithm.
  arXiv  Detail & Related papers  (2024-09-04T15:11:55Z)
• Supervised Fine-Tuning as Inverse Reinforcement Learning [8.044033685073003]
  The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback. In our work, we question the efficacy of such datasets and explore various scenarios where alignment with expert demonstrations proves more realistic.
  arXiv  Detail & Related papers  (2024-03-18T17:52:57Z)
• 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)
• KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All [24.50129285997307]
  We introduce a novel key-query learning strategy to enhance prompt matching efficiency and address the challenge of shifting features. Our method empowers the model to achieve results surpassing those of current state-of-the-art approaches by a large margin of up to 20%.
  arXiv  Detail & Related papers  (2023-11-26T20:35:19Z)
• Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models [79.32652077838046]
  We introduce Parrot, a solution aiming to enhance multi-turn instruction following for large language models (LLMs) First, we introduce an efficient but effective method for collecting multi-turn instructions that feature human-like queries, such as anaphora and ellipsis. Second, we propose a context-aware preference optimization strategy to further enhance LLMs for complex queries in multi-turn interaction.
  arXiv  Detail & Related papers  (2023-10-11T08:36:43Z)
• Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL [62.824464372594576]
  We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization. We identify a previously overlooked objective of query dependency in such optimization. We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
  arXiv  Detail & Related papers  (2023-09-13T01:12:52Z)
• DEPHN: Different Expression Parallel Heterogeneous Network using virtual gradient optimization for Multi-task Learning [1.0705399532413615]
  Recommendation system algorithm based on multi-task learning (MTL) is the major method for Internet operators to understand users and predict their behaviors. Traditional models use shared-bottom models and gating experts to realize shared representation learning and information differentiation. We propose an Different Expression Parallel Heterogeneous Network (DEPHN) to model multiple tasks simultaneously.
  arXiv  Detail & Related papers  (2023-07-24T04:29:00Z)
• Hierarchical Optimization-Derived Learning [58.69200830655009]
  We establish a new framework, named Hierarchical ODL (HODL), to simultaneously investigate the intrinsic behaviors of optimization-derived model construction and its corresponding learning process. This is the first theoretical guarantee for these two coupled ODL components: optimization and learning.
  arXiv  Detail & Related papers  (2023-02-11T03:35:13Z)
• Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch [13.024115985194932]
  We propose a new approach for solving the data labeling and inference issues in optimization based on the use of the reinforcement learning (RL) paradigm. We use imitation learning to bootstrap an RL agent and then use Proximal Policy (PPO) to further explore global optimal actions.
  arXiv  Detail & Related papers  (2022-06-14T16:35:58Z)
• Contrastive Instruction-Trajectory Learning for Vision-Language Navigation [66.16980504844233]
  A vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works fail to discriminate the similarities and discrepancies across instruction-trajectory pairs and ignore the temporal continuity of sub-instructions. We propose a Contrastive Instruction-Trajectory Learning framework that explores invariance across similar data samples and variance across different ones to learn distinctive representations for robust navigation.
  arXiv  Detail & Related papers  (2021-12-08T06:32:52Z)
• Provable Representation Learning for Imitation Learning via Bi-level Optimization [60.059520774789654]
  A common strategy in modern learning systems is to learn a representation that is useful for many tasks. We study this strategy in the imitation learning setting for Markov decision processes (MDPs) where multiple experts' trajectories are available. We instantiate this framework for the imitation learning settings of behavior cloning and observation-alone.
  arXiv  Detail & Related papers  (2020-02-24T21:03:52Z)

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.