Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuning

• URL: http://arxiv.org/abs/2505.11922v1
• Date: Sat, 17 May 2025 09:13:47 GMT
• Title: Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuning
• Authors: Yuheng Lu, ZiMeng Bai, Caixia Yuan, Huixing Jiang, Xiaojie Wang,
• Abstract summary: Post-training large language models (LLMs) may struggle to consistently follow complex instructions.<n>We propose transforming sequentially structured input instruction into multiple parallel instructions containing subcontexts.<n>MISO introduces a mixture-of-contexts paradigm that jointly considers the overall instruction-output alignment and the influence of individual sub-contexts to enhance SFT effectiveness.
• Score: 13.56631686493347
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) exhibit remarkable capabilities in handling natural language tasks; however, they may struggle to consistently follow complex instructions including those involve multiple constraints. Post-training LLMs using supervised fine-tuning (SFT) is a standard approach to improve their ability to follow instructions. In addressing complex instruction following, existing efforts primarily focus on data-driven methods that synthesize complex instruction-output pairs for SFT. However, insufficient attention allocated to crucial sub-contexts may reduce the effectiveness of SFT. In this work, we propose transforming sequentially structured input instruction into multiple parallel instructions containing subcontexts. To support processing this multi-input, we propose MISO (Multi-Input Single-Output), an extension to currently dominant decoder-only transformer-based LLMs. MISO introduces a mixture-of-contexts paradigm that jointly considers the overall instruction-output alignment and the influence of individual sub-contexts to enhance SFT effectiveness. We apply MISO fine-tuning to complex instructionfollowing datasets and evaluate it with standard LLM inference. Empirical results demonstrate the superiority of MISO as a fine-tuning method for LLMs, both in terms of effectiveness in complex instruction-following scenarios and its potential for training efficiency.

Related papers

• 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.<n>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)
• Constraint Back-translation Improves Complex Instruction Following of Large Language Models [55.60192044049083]
  Large language models (LLMs) struggle to follow instructions with complex constraints in format, length, etc.<n>Previous works conduct post-training on complex instruction-response pairs generated by feeding complex instructions to advanced LLMs.<n>We propose a novel data generation technique, constraint back-translation.
  arXiv  Detail & Related papers  (2024-10-31T17:42:26Z)
• SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe [30.03925858123481]
  Large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP)<n>Efforts to improve instruction tuning often focus on higher-quality supervised fine-tuning (SFT) datasets.<n>We propose SFTMix, a novel Mixup-based recipe that LLM instruction tuning beyond the conventional NTP paradigm.
  arXiv  Detail & Related papers  (2024-10-07T17:52:21Z)
• CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
  In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives. Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance. In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
  arXiv  Detail & Related papers  (2024-07-29T23:18:55Z)
• Enhancing LLM's Cognition via Structurization [41.13997892843677]
  Large language models (LLMs) process input contexts through a causal and sequential perspective. This paper presents a novel concept of context structurization. Specifically, we transform the plain, unordered contextual sentences into well-ordered and hierarchically structurized elements.
  arXiv  Detail & Related papers  (2024-07-23T12:33:58Z)
• Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants [28.691691883519542]
  We introduce a technique that decomposes complex instructions into simpler sub-components, modifies these, and reconstructs them into new variants. Based on DeMoRecon, we developed the FGIV dataset which contains fine-grained instruction variants of 1,773 seed instructions. Our findings show that LLMs fine-tuned with FGIV will gain significant performance boost on both ours and commonly used instructions-following benchmarks.
  arXiv  Detail & Related papers  (2024-06-17T08:08:11Z)
• From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models [43.869374263102934]
  We study what training data is effective in enhancing complex constraints following abilities. We find that training LLMs with instructions containing multiple constraints enhances their understanding of complex instructions. Our methods improve models' ability to follow instructions generally and generalize effectively across out-of-domain, in-domain, and adversarial settings.
  arXiv  Detail & Related papers  (2024-04-24T12:51:14Z)
• Can Large Language Models Understand Real-World Complex Instructions? [54.86632921036983]
  Large language models (LLMs) can understand human instructions, but struggle with complex instructions. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions. We propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
  arXiv  Detail & Related papers  (2023-09-17T04:18:39Z)
• FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning [70.38817963253034]
  This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution. We provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings.
  arXiv  Detail & Related papers  (2023-09-01T09:40:36Z)
• 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)
• Instruction Tuning for Large Language Models: A Survey [52.86322823501338]
  We make a systematic review of the literature, including the general methodology of supervised fine-tuning (SFT)<n>We also review the potential pitfalls of SFT along with criticism against it, along with efforts pointing out current deficiencies of existing strategies.
  arXiv  Detail & Related papers  (2023-08-21T15:35:16Z)

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.