Logo image
Back
Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
Preprint   Open access

Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries

Kiran Vodrahalli, Santiago Ontanon, Nilesh Tripuraneni, Kelvin Xu, Sanil Jain, Rakesh Shivanna, Jeffrey Hui, Nishanth Dikkala, Mehran Kazemi, Bahare Fatemi, …
19 Sep 2024
DOI: https://doi.org/10.48550/arxiv.2409.12640
url
https://arxiv.org/abs/2409.12640View
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute,  Open

Abstract

Computer Science - Computation and Language Computer Science - Learning
We introduce Michelangelo: a minimal, synthetic, and unleaked long-context reasoning evaluation for large language models which is also easy to automatically score. This evaluation is derived via a novel, unifying framework for evaluations over arbitrarily long contexts which measure the model's ability to do more than retrieve a single piece of information from its context. The central idea of the Latent Structure Queries framework (LSQ) is to construct tasks which require a model to ``chisel away'' the irrelevant information in the context, revealing a latent structure in the context. To verify a model's understanding of this latent structure, we query the model for details of the structure. Using LSQ, we produce three diagnostic long-context evaluations across code and natural-language domains intended to provide a stronger signal of long-context language model capabilities. We perform evaluations on several state-of-the-art models and demonstrate both that a) the proposed evaluations are high-signal and b) that there is significant room for improvement in synthesizing long-context information.

Metrics

20 Record Views

Details

Logo image