LOOM-Scope: a comprehensive and efficient LOng-cOntext Model evaluation framework
This addresses the need for reliable and accessible evaluation tools for researchers and developers working on long-context models, though it is incremental as it builds on existing benchmarks.
The paper tackles the problem of inconsistent and computationally expensive evaluation of long-context language models by proposing LOOM-Scope, a framework that standardizes settings, supports efficient inference, and introduces a lightweight benchmark suite.
Long-context processing has become a fundamental capability for large language models~(LLMs). To assess model's long-context performance, numerous long-context evaluation benchmarks have been proposed. However, variations in evaluation settings across these benchmarks lead to inconsistent results, making it difficult to draw reliable comparisons. Besides, the high computational cost of long-context evaluation poses a significant barrier for the community to conduct comprehensive assessments of long-context models. In this paper, we propose LOOM-Scope, a comprehensive and efficient framework for long-context evaluation. LOOM-Scope standardizes evaluation settings across diverse benchmarks, supports deployment of efficient long-context inference acceleration methods, and introduces a holistic yet lightweight benchmark suite to evaluate models comprehensively. Homepage: https://loomscope.github.io