Correlated Errors in Large Language Models

• URL: http://arxiv.org/abs/2506.07962v1
• Date: Mon, 09 Jun 2025 17:37:18 GMT
• Title: Correlated Errors in Large Language Models
• Authors: Elliot Kim, Avi Garg, Kenny Peng, Nikhil Garg,
• Abstract summary: We find substantial correlation in model errors on a leaderboard dataset.<n>We identify factors driving model correlation, including shared architectures and providers.<n>We show the effects of correlation in two downstream tasks: LLM-as-judge evaluation and hiring.
• Score: 0.6856888934092934
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diversity in training data, architecture, and providers is assumed to mitigate homogeneity in LLMs. However, we lack empirical evidence on whether different LLMs differ meaningfully. We conduct a large-scale empirical evaluation on over 350 LLMs overall, using two popular leaderboards and a resume-screening task. We find substantial correlation in model errors -- on one leaderboard dataset, models agree 60% of the time when both models err. We identify factors driving model correlation, including shared architectures and providers. Crucially, however, larger and more accurate models have highly correlated errors, even with distinct architectures and providers. Finally, we show the effects of correlation in two downstream tasks: LLM-as-judge evaluation and hiring -- the latter reflecting theoretical predictions regarding algorithmic monoculture.

Related papers

• Using Large Language Models to Assess Teachers' Pedagogical Content Knowledge [3.2489371952043213]
  This study examines whether large language models introduce construct-irrelevant variance (CIV) in ways similar to or different from machine learning (ML) and human raters.<n>Using generalized linear mixed models (GLMMs), we compared variance components and rater-level scoring patterns across three scoring sources.<n>Results indicate that scenario-level variance was minimal across tasks, while rater-related factors contributed substantially to CIV.
  arXiv  Detail & Related papers  (2025-05-25T18:45:53Z)
• Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric [99.56567010306807]
  Large Language Models (LLMs) have become indispensable across academia, industry, and daily applications.<n>One core challenge of evaluation in the large language model (LLM) era is the generalization issue.<n>We propose Model Utilization Index (MUI), a mechanism interpretability enhanced metric that complements traditional performance scores.
  arXiv  Detail & Related papers  (2025-04-10T04:09:47Z)
• LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning [39.54891426369773]
  Trade-offs between model size, architecture, and performance remain underexplored.<n>In this paper, we introduce LLaVA-MORE, a new family of MLLMs that integrates recent language models with diverse visual backbones.<n>To ensure fair comparisons, we employ a unified training protocol applied consistently across all architectures.
  arXiv  Detail & Related papers  (2025-03-19T18:10:12Z)
• ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models [75.05436691700572]
  We introduce ExpliCa, a new dataset for evaluating Large Language Models (LLMs) in explicit causal reasoning.<n>We tested seven commercial and open-source LLMs on ExpliCa through prompting and perplexity-based metrics.<n>Surprisingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events.
  arXiv  Detail & Related papers  (2025-02-21T14:23:14Z)
• Preference Leakage: A Contamination Problem in LLM-as-a-judge [69.96778498636071]
  Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods.<n>In this work, we expose preference leakage, a contamination problem in LLM-as-a-judge caused by the relatedness between the synthetic data generators and LLM-based evaluators.
  arXiv  Detail & Related papers  (2025-02-03T17:13:03Z)
• LLMs and the Madness of Crowds [0.0]
  We analyze the patterns of incorrect answers produced by large language models (LLMs) during evaluation. Our findings reveal that the incorrect responses are not randomly distributed but systematically correlated across models.
  arXiv  Detail & Related papers  (2024-11-03T12:03:12Z)
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models [42.17166746027585]
  We introduce a bidirectional weighted graph-based framework to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $beta$-VAE based module to extract factors as the initial nodes of the graph. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement.
  arXiv  Detail & Related papers  (2024-07-26T15:32:21Z)
• Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models [56.02275285521847]
  We propose to evaluate models using a Panel of LLm evaluators (PoLL) We find that using a PoLL composed of a larger number of smaller models outperforms a single large judge, exhibits less intra-model bias due to its composition of disjoint model families, and does so while being over seven times less expensive.
  arXiv  Detail & Related papers  (2024-04-29T15:33:23Z)
• Can Large Language Models Infer Causation from Correlation? [104.96351414570239]
  We test the pure causal inference skills of large language models (LLMs) We formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables. We show that these models achieve almost close to random performance on the task.
  arXiv  Detail & Related papers  (2023-06-09T12:09:15Z)
• Non-Invasive Fairness in Learning through the Lens of Data Drift [88.37640805363317]
  We show how to improve the fairness of Machine Learning models without altering the data or the learning algorithm. We use a simple but key insight: the divergence of trends between different populations, and, consecutively, between a learned model and minority populations, is analogous to data drift. We explore two strategies (model-splitting and reweighing) to resolve this drift, aiming to improve the overall conformance of models to the underlying data.
  arXiv  Detail & Related papers  (2023-03-30T17:30:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.