WritingBench: A Comprehensive Benchmark for Generative Writing
This addresses the problem of limited evaluation benchmarks for high-quality writing across diverse domains, though it is incremental as it builds on existing text generation frameworks.
The authors tackled the challenge of evaluating large language models in generative writing by introducing WritingBench, a comprehensive benchmark covering 6 core domains and 100 subdomains, which enabled 7B-parameter models to approach state-of-the-art performance.
Recent advancements in large language models (LLMs) have significantly enhanced text generation capabilities, yet evaluating their performance in generative writing remains a challenge. Existing benchmarks primarily focus on generic text generation or limited in writing tasks, failing to capture the diverse requirements of high-quality written contents across various domains. To bridge this gap, we present WritingBench, a comprehensive benchmark designed to evaluate LLMs across 6 core writing domains and 100 subdomains, encompassing creative, persuasive, informative, and technical writing. We further propose a query-dependent evaluation framework that empowers LLMs to dynamically generate instance-specific assessment criteria. This framework is complemented by a fine-tuned critic model for criteria-aware scoring, enabling evaluations in style, format and length. The framework's validity is further demonstrated by its data curation capability, which enables 7B-parameter models to approach state-of-the-art (SOTA) performance. We open-source the benchmark, along with evaluation tools and modular framework components, to advance the development of LLMs in writing.