paper-with-me

홈 › Papers

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

2025-05-17 · Yuheng Lu, ZiMeng Bai, Caixia Yuan, Huixing Jiang, Xiaojie Wang

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.

📄 PDF Abstract BibTeX arXiv:2505.11922

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderInstruction Following

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
Focus 설명 없음
SFT Shrink and Fine-Tune, or SFT, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning.…

Similar Papers 제목 키워드 기반

From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models

2024-04-24 · Qianyu He, Jie Zeng, Qianxi He, Jiaqing Liang 외

It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i.e. Complex Instructions Following). Yet, it remains under-explored how to enhance the ability of LLMs to follow comp…

Instruction Following

Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants

2024-06-17 · Jiuding Yang, Weidong Guo, Kaitong Yang, Xiangyang Li 외

The effective alignment of Large Language Models (LLMs) with precise instructions is essential for their application in diverse real-world scenarios. Current methods focus on enhancing the diversity and complexity of tra…

Data AugmentationDiversityInstruction Following

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

2026-02-04 · Yuancheng Yang, Lin Yang, Xu Wang, Chao Tong 외 arxiv

As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruct…

Reinforcement LearningInstruction Following

GraphIF: Enhancing Multi-Turn Instruction Following for Large Language Models with Relation Graph Prompt

2025-11-13 · Zhenhe Li, Can Lin, Ling Zheng, Wen-Da Wei 외 arxiv

Multi-turn instruction following is essential for building intelligent conversational systems that can consistently adhere to instructions across dialogue turns. However, existing approaches to enhancing multi-turn instr…

Instruction FollowingRelation ExtractionResponse Generation

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models

2023-10-11 · Yuchong Sun, Che Liu, Kun Zhou, Jinwen Huang 외

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLM…

AttributeInstruction Following