ScopeIF Framework for LLM Instruction Following
ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling
ScopeIF addresses a critical gap in LLM training by providing dense supervision for complex constraints that existing binary reward models miss. This approach significantly improves performance on multi-faceted instructions without compromising general capabilities. Developers working with complex task automation can implement this framework to enhance their models' precision, particularly when dealing with segmented constraints across different response parts.
ScopeIF introduces a training framework that improves precise instruction-following in large language models by addressing constraint scope diversity.
The method uses a unified schema that factorizes constraints into Scope, Target, and Range dimensions.Researchers constructed ScopeInstruct, a large-scale instruction dataset with diverse scope-aware constraints, and combined tool-grounded verification with graded reward modeling.
Experiments show ScopeIF enables optimized Qwen3-4B and 8B models to rival or surpass Gemini-2.5-Pro and DeepSeek-V3.
2 on complex constraints.
ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling
Precise instruction-following is a fundamental ability of large language models (LLMs), requiring their outputs to strictly satisfy objective constraints in input instructions. In complex application scenarios, these constraints often possess diverse scopes that govern specific response segments rather than the entire output. However, existing optimization methods often neglect constraint scope during data construction and rely on binary per-constraint rewards, yielding limited data diversity and sparse supervision for complex constraints. To this end, we propose ScopeIF, a novel training framework for scope-aware precise instruction-following. We first introduce a unified schema that factorizes objective constraints into three decoupled dimensions: Scope, Target, and Range. Grounded in this schema, we construct ScopeInstruct, a large-scale instruction dataset with diverse scope-aware constraints, and combine tool-grounded verification with graded reward modeling to quantify the violation degree of each constraint, providing dense supervision for policy optimization. Extensive experiments demonstrate that ScopeIF consistently outperforms existing methods, particularly on complex scope-aware constraints, while preserving general capabilities. Notably, it enables optimized Qwen3-4B and 8B models to rival or surpass strong frontier models such as Gemini-2.5-Pro and DeepSeek-V3.2, establishing an effective paradigm for advancing scope-aware instruction-following. Our code and data are available at https://github.com/thu-coai/ScopeIF.
This report is categorized under AITOP's "Papers" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include ScopeIF, Qwen3, Gemini-2.5-Pro, DeepSeek-V3.2.
Primary source verification: published directly by arXiv: DeepSeek with first-party authority.
