# Likelihood Variance as Text Importance for Resampling Texts to Map Language Models

arXiv: https://arxiv.org/abs/2505.15428 · HTML: https://mlsanity.com/paper/2505.15428/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 10 of 10)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [We Should Chart an Atlas of All the World's Models](https://mlsanity.com/paper/2503.10633/) (2025)
- [PhyloLM : Inferring the Phylogeny of Large Language Models and Predicting their Performances in Benchmarks](https://mlsanity.com/paper/2404.04671/) (2024)
- [Mapping 1,000+ Language Models via the Log-Likelihood Vector](https://mlsanity.com/paper/2502.16173/) (2025)
- [Higher-order accuracy of multiscale-double bootstrap for testing regions](https://mlsanity.com/paper/1312.6348/) (2013)

## Built on by (most cited first, 3 of 3)

- [Map of Encoders -- Mapping Sentence Encoders using Quantum Relative Entropy](https://mlsanity.com/paper/2602.08740/) (2026)
- [Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target Model](https://mlsanity.com/paper/2603.16622/) (2026)
- [Language Model Maps for Prompt-Response Distributions via Log-Likelihood Vectors](https://mlsanity.com/paper/2603.18593/) (2026)

## Abstract (arXiv)

We address the computational cost of constructing a model map, which embeds diverse language models into a common space for comparison via KL divergence. The map relies on log-likelihoods over a large text set, making the cost proportional to the number of texts. To reduce this cost, we propose a resampling method that selects important texts with weights proportional to the variance of log-likelihoods across models for each text. Our method significantly reduces the number of required texts while preserving the accuracy of KL divergence estimates. Experiments show that it achieves comparable performance to uniform sampling with about half as many texts, and also facilitates efficient incorporation of new models into an existing map. These results enable scalable and efficient construction of language model maps.