CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models

• URL: http://arxiv.org/abs/2607.24999v1
• Date: Mon, 27 Jul 2026 18:56:13 GMT
• Title: CogArena: A Multimethod Evaluation of Cognitive Ability Structure in Large Language Models
• Abstract summary: We introduce CogArena, a benchmark for determining when cognitive-task scores warrant dimensional labels.<n>Across 55 open-weight models, nearly all paradigm correlations are positive and a common axis explains about half the variance.<n>The within-grouping advantage is small, scoring-sensitive, and uncertain across model families.
• Score: 3.991518853474585
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM cognitive scores are increasingly summarized as per-ability profiles whose dimensions should converge across tasks, respond selectively to matched interventions, and generalize beyond the models used to define them. We introduce CogArena, a procedurally generated 13-paradigm benchmark built around a multimethod framework for determining when cognitive-task scores warrant dimensional labels across five theory-motivated groupings. Across 55 open-weight models, nearly all paradigm correlations are positive and a common axis explains about half the variance. The within-grouping advantage is small, scoring-sensitive, and uncertain across model families. In a separately frozen, fully crossed study across 12 models from six families, targeted scaffolds show a small matched-grouping advantage, but no scaffold-specific contrast survives multiplicity correction and selectivity does not improve held-out-family prediction. The frozen confirmation criterion fails. A post-hoc alternate-wording replication produces a smaller positive estimate and again fails. Together, these results support a boundary conclusion. Theory-aligned prompting produces a small in-battery diagonal tendency, but the present evidence does not establish stable five-dimensional profiles. CogArena provides a workflow joining behavioral signatures, covariance, matched interventions, and out-of-family prediction before cognitive labels are attached to model scores.

Related papers

• Mapping and Measuring the Behavioral Evolution of Large Language Models [28.603443859513153]
  Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations.<n>We characterize the output behavior of 32 models from six families using their responses to a shared bank of 10,000 prompts.
  arXiv  Detail & Related papers  (2026-08-11T15:07:28Z)
• Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement [66.67463557274358]
  Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes.<n>We introduce Confidence-guided Concept Mining (CBCM) to identify reliable spurious attributes without attribute annotations.<n>We propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches.
  arXiv  Detail & Related papers  (2026-06-23T05:28:47Z)
• The Ghost Annotator: a Framework to Explore Human Label Variation in Content Moderation through Conformal Prediction [39.10305114526259]
  We introduce a framework combining conformal prediction with Collaborative Filtering-style annotators' representation.<n>Using Non-Conformity Scores, we introduce the Ghost Prediction metric and the Ghost Annotator representation to quantify cases in which model predictions diverge from all available human annotations.<n>Our finding shows that while all models uncertainty increases with annotator disagreement, larger models tend to be more confident in the classification of texts that are not aligned with any human annotation.
  arXiv  Detail & Related papers  (2026-06-01T21:32:37Z)
• Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap [75.41420283374737]
  Overlap is a key condition for causal treatment effect estimation.<n>We propose a class of feature representations called deconfounding scores.<n>We show that prognostic scores are overlap-optimal within this class.
  arXiv  Detail & Related papers  (2026-04-01T12:19:42Z)
• Conditioning Protein Generation via Hopfield Pattern Multiplicity [0.0]
  Protein sequence generation via geometric attention produces plausible family members from small alignments without training.<n>We show that a single scalar parameter, added as a bias to the sampler's attention logits, continuously shifts generation from the full family toward a user-specified subset.<n>Experiments on five Pfam families confirm the monotonic relationship between separation and gap across a fourfold range of geometries.
  arXiv  Detail & Related papers  (2026-03-20T16:38:15Z)
• The Lie of the Average: How Class Incremental Learning Evaluation Deceives You? [48.83567710215299]
  Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones.<n>We argue that a robust CIL evaluation protocol should accurately characterize and estimate the entire performance distribution.<n>We propose EDGE, an evaluation protocol that adaptively identifies and samples extreme class sequences using inter-task similarity.
  arXiv  Detail & Related papers  (2025-09-26T17:00:15Z)
• ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models [26.544938760265136]
  Deep learning models inadvertently learn spurious correlations between targets and non-essential features.<n>In this paper, we propose a novel post hoc spurious bias mitigation framework without requiring group labels.<n>Our framework, termed ShortcutProbe, identifies prediction shortcuts that reflect potential non-robustness in predictions in a given model's latent space.
  arXiv  Detail & Related papers  (2025-05-20T04:21:17Z)
• Multi-Level Collaboration in Model Merging [56.31088116526825]
  This paper explores the intrinsic connections between model merging and model ensembling.<n>We find that even when previous restrictions are not met, there is still a way for model merging to attain a near-identical and superior performance similar to that of ensembling.
  arXiv  Detail & Related papers  (2025-03-03T07:45:04Z)
• Model-Agnostic Covariate-Assisted Inference on Partially Identified Causal Effects [1.9253333342733674]
  Many causal estimands are only partially identifiable since they depend on the unobservable joint distribution between potential outcomes. We propose a unified and model-agnostic inferential approach for a wide class of partially identified estimands.
  arXiv  Detail & Related papers  (2023-10-12T08:17:30Z)
• Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding [49.1865229301561]
  We present a simple approach to partial identification using existing causal sensitivity models and show empirically that Caus-Modens gives tighter outcome intervals. The last of our three diverse benchmarks is a novel usage of GPT-4 for observational experiments with unknown but probeable ground truth.
  arXiv  Detail & Related papers  (2023-06-15T21:42:40Z)
• Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation [74.06904875527556]
  We propose a generic and efficient segmentation framework to construct ensemble segmentation models. In the proposed method, ensemble models can be efficiently generated by using the layer selection method. We also devise a new pixel-wise uncertainty loss, which improves the predictive performance.
  arXiv  Detail & Related papers  (2020-05-21T16:08:38Z)

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.