paper-with-me

홈 › Papers

LIFEBench: Evaluating Length Instruction Following in Large Language Models

2025-05-22 · Wei zhang, Zhenhong Zhou, Junfeng Fang, Rongwu Xu, Kun Wang, Yuanhe Zhang, Rui Wang, Ge Zhang, Xinfeng Li, Li Sun, Lingjuan Lyu, Yang Liu, Sen Su

While large language models (LLMs) can solve PhD-level reasoning problems over long context inputs, they still struggle with a seemingly simpler task: following explicit length instructions-e.g., write a 10,000-word novel. Additionally, models often generate far too short outputs, terminate prematurely, or even refuse the request. Existing benchmarks focus primarily on evaluating generations quality, but often overlook whether the generations meet length constraints. To this end, we introduce Length Instruction Following Evaluation Benchmark (LIFEBench) to comprehensively evaluate LLMs' ability to follow length instructions across diverse tasks and a wide range of specified lengths. LIFEBench consists of 10,800 instances across 4 task categories in both English and Chinese, covering length constraints ranging from 16 to 8192 words. We evaluate 26 widely-used LLMs and find that most models reasonably follow short-length instructions but deteriorate sharply beyond a certain threshold. Surprisingly, almost all models fail to reach the vendor-claimed maximum output lengths in practice, as further confirmed by our evaluations extending up to 32K words. Even long-context LLMs, despite their extended input-output windows, counterintuitively fail to improve length-instructions following. Notably, Reasoning LLMs outperform even specialized long-text generation models, achieving state-of-the-art length following. Overall, LIFEBench uncovers fundamental limitations in current LLMs' length instructions following ability, offering critical insights for future progress.

📄 PDF Abstract BibTeX arXiv:2505.16234

Code (1)

lifebench/lifebench 공식 구현

Tasks

Instruction FollowingText Generation

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Prompt-Based One-Shot Exact Length-Controlled Generation with LLMs

2025-08-19 · Juncheng Xie, Hung-yi Lee arxiv

Controlling the length of text produced by large language models (LLMs) remains challenging: models frequently overshoot or undershoot explicit length instructions because they cannot reliably keep an internal token coun…

Instruction FollowingPrompt Engineering

CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation

2025-03-05 · Peiding Wang, Li Zhang, Fang Liu, Lin Shi 외

Large Language Models (LLMs) have demonstrated exceptional performance in code generation tasks and have become indispensable programming assistants for developers. However, existing code generation benchmarks primarily …

Code GenerationInstruction Following

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

2025-05-20 · Tingchen Fu, Jiawei Gu, Yafu Li, Xiaoye Qu 외

Instruction-following is essential for aligning large language models (LLMs) with user intent. While recent reasoning-oriented models exhibit impressive performance on complex mathematical problems, their ability to adhe…

Instruction FollowingMathematical Reasoning

LongAlign: A Recipe for Long Context Alignment of Large Language Models

2024-01-31 · Yushi Bai, Xin Lv, Jiajie Zhang, Yuze He 외

Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, traini…

DiversityInstruction Following

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios

2024-11-11 · Xiaodong Wu, Minhao Wang, Yichen Liu, Xiaoming Shi 외

As Large Language Models (LLMs) evolve in natural language processing (NLP), their ability to stably follow instructions in long-context inputs has become critical for real-world applications. However, existing benchmark…

Instruction Following