Cover Image

DecIF: Improving Instruction-Following through Meta-Decomposition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hui, Tingfeng, Zhu, Pengyu, Ping, Bowen, Tang, Ling, Dong, Guanting, Zhang, Yaqi, Su, Sen
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Smaller Language Models Are Better Instruction Evolvers
by: Hui, Tingfeng, et al.
Published: (2024)

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
by: Hui, Tingfeng, et al.
Published: (2024)

STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
by: Hui, Tingfeng, et al.
Published: (2026)

Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
by: Zhao, Jinxu, et al.
Published: (2024)

Toward General Instruction-Following Alignment for Retrieval-Augmented Generation
by: Dong, Guanting, et al.
Published: (2024)

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
by: Dong, Guanting, et al.
Published: (2024)

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards
by: Ping, Bowen, et al.
Published: (2026)

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following
by: Lou, Renze, et al.
Published: (2023)

LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
by: Ping, Bowen, et al.
Published: (2026)

LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
by: Zhang, Wei, et al.
Published: (2026)

Following Length Constraints in Instructions
by: Yuan, Weizhe, et al.
Published: (2024)

Improving Instruction-Following in Language Models through Activation Steering
by: Stolfo, Alessandro, et al.
Published: (2024)

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
by: Huang, Hui, et al.
Published: (2025)

LIFEBench: Evaluating Length Instruction Following in Large Language Models
by: Zhang, Wei, et al.
Published: (2025)

M3PO: Multimodal-Model-Guided Preference Optimization for Visual Instruction Following
by: Gao, Ruirui, et al.
Published: (2025)

MedINST: Meta Dataset of Biomedical Instructions
by: Han, Wenhan, et al.
Published: (2024)

CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
by: Liu, Yilun, et al.
Published: (2023)

Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
by: Lee, JoonHo, et al.
Published: (2024)

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
by: Wen, Bosi, et al.
Published: (2026)

Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
by: Tang, Yinghao, et al.
Published: (2026)

Learning Instruction-Following Policies through Open-Ended Instruction Relabeling with Large Language Models
by: Zhang, Zhicheng, et al.
Published: (2025)

Instruction Following without Instruction Tuning
by: Hewitt, John, et al.
Published: (2024)

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
by: Cheng, Jiale, et al.
Published: (2024)

DotaMath: Decomposition of Thought with Code Assistance and Self-correction for Mathematical Reasoning
by: Li, Chengpeng, et al.
Published: (2024)

CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
by: Zhang, Kaiyan, et al.
Published: (2024)

MDCure: A Scalable Pipeline for Multi-Document Instruction-Following
by: Liu, Gabrielle Kaili-May, et al.
Published: (2024)

FollowTable: A Benchmark for Instruction-Following Table Retrieval
by: Jin, Rihui, et al.
Published: (2026)

DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs
by: Huang, Minghui
Published: (2025)

IHEval: Evaluating Language Models on Following the Instruction Hierarchy
by: Zhang, Zhihan, et al.
Published: (2025)

GraphWiz: An Instruction-Following Language Model for Graph Problems
by: Chen, Nuo, et al.
Published: (2024)

MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making
by: Fu, Dayuan, et al.
Published: (2024)

IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation
by: Wen, Bosi, et al.
Published: (2025)

Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models
by: Sun, Haoran, et al.
Published: (2024)

IFDECORATOR: Wrapping Instruction Following Reinforcement Learning with Verifiable Rewards
by: Guo, Xu, et al.
Published: (2025)

MetaAlign: Align Large Language Models with Diverse Preferences during Inference Time
by: Zhang, Mozhi, et al.
Published: (2024)

Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency
by: Yang, Shu, et al.
Published: (2026)

TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation
by: Zhu, He, et al.
Published: (2025)

In-Context Examples Matter: Improving Emotion Recognition in Conversation with Instruction Tuning
by: Ma, Hui, et al.
Published: (2025)

Generalizing Verifiable Instruction Following
by: Pyatkin, Valentina, et al.
Published: (2025)

Revisiting the Reliability of Language Models in Instruction-Following
by: Dong, Jianshuo, et al.
Published: (2025)