paper-with-me

홈 › Papers

A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models

2025-05-12 · Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao shi, Jianping Fan, Xuanjing Huang

Instruction following evaluates large language models (LLMs) on their ability to generate outputs that adhere to user-defined constraints. However, existing benchmarks often rely on templated constraint prompts, which lack the diversity of real-world usage and limit fine-grained performance assessment. To fill this gap, we propose a multi-dimensional constraint framework encompassing three constraint patterns, four constraint categories, and four difficulty levels. Building on this framework, we develop an automated instruction generation pipeline that performs constraint expansion, conflict detection, and instruction rewriting, yielding 1,200 code-verifiable instruction-following test samples. We evaluate 19 LLMs across seven model families and uncover substantial variation in performance across constraint forms. For instance, average performance drops from 77.67% at Level I to 32.96% at Level IV. Furthermore, we demonstrate the utility of our approach by using it to generate data for reinforcement learning, achieving substantial gains in instruction following without degrading general performance. In-depth analysis indicates that these gains stem primarily from modifications in the model's attention modules parameters, which enhance constraint recognition and adherence. Code and data are available in https://github.com/Junjie-Ye/MulDimIF.

📄 PDF Abstract BibTeX arXiv:2505.07591

Code (1)

junjie-ye/muldimif 공식 구현 pytorch

Tasks

Instruction 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

Similar Papers 제목 키워드 기반

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs

2024-08-02 · Chenglin Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang 외

The adeptness of Large Language Models (LLMs) in comprehending and following natural language instructions is critical for their deployment in sophisticated real-world applications. Existing evaluations mainly focus on f…

RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation

2026-06-01 · Huiqiong Li, Jiayu Wang, Zhiting Mei, Anirudha Majumdar 외 arxiv

Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and safe instructions. We introduce RoboTrustBench, a benchmark for evaluating the tru…

Instruction Following

FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models

2023-10-31 · Yuxin Jiang, YuFei Wang, Xingshan Zeng, Wanjun Zhong 외

The ability to follow instructions is crucial for Large Language Models (LLMs) to handle various real-world applications. Existing benchmarks primarily focus on evaluating pure response quality, rather than assessing whe…

Instruction Following

VCIFBench: Evaluating Complex Instruction Following for Video Understanding

2026-06-03 · Huangchen Xu, Yuan Wu, Yi Chang arxiv

Multimodal large language models have made rapid progress in video understanding, yet existing benchmarks largely rely on simple prompts and provide limited evidence about whether models can satisfy explicit output const…

Instruction Following

Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding Scenarios

2026-08-26 · Hongbo Liu, Peixian Chen, Sihan Liu, Peiyuan Zhang 외 arxiv

Multimodal Large Language Models (MLLMs) have shown strong performance in video understanding. However, their ability to follow instructions in this domain remains under-explored. Real-world video understanding requires …

Instruction Following