Mapping and Measuring the Behavioral Evolution of Large Language Models

• URL: http://arxiv.org/abs/2608.11027v1
• Date: Tue, 11 Aug 2026 15:07:28 GMT
• Title: Mapping and Measuring the Behavioral Evolution of Large Language Models
• Abstract summary: 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.
• Score: 28.603443859513153
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations. We characterize the output behavior of 32 models from six families using their responses to a shared bank of 10{,}000 prompts. After embedding each response, we construct three complementary sentence-level dissimilarities: an aligned mean per-prompt distance, which is a pseudometric on observed model responses; a PCA-compressed summary of prompt-wise disagreement; and an alignment-free Gromov--Wasserstein discrepancy between models' internal response geometries. We use these constructions to study static organization and temporal change on a release-date axis through behavioral maps, family-wise drift, hierarchical clustering, cross-family convergence, and response-cloud dispersion. Across the three constructions, model families form coherent clusters, with \texttt{gpt-2} as a global outlier; cross-family distances decrease over time; and several recent reasoning-oriented models have comparatively compact response clouds. A token-level cross-check based on per-prompt Maximum Mean Discrepancy closely agrees with the sentence-level mean distance (Spearman $ρ=0.98$) and recovers the same qualitative findings. We organize these comparisons through a measure-theoretic lens making their alignment and invariance assumptions explicit. We also establish an architecture-agnostic sufficient condition linking behavioral similarity to inference-prompt coverage, small excess population log-loss, and similar effective target distributions---a possible training-side account rather than an empirical explanation of the observed trends. Our pipeline is label-free, and re-encoding every response with three further encoders---down to one $73\times$ smaller---preserves the rank geometry, the outliers, and the sign of the time trend.

Related papers

• Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights [0.40611352512781873]
  We introduce a Rater Ising-Potts model that uses agreement indicators between ratings and category labels.<n>We evaluate the model on three constructed-response datasets spanning a corpus of K=14,466 short answers on a three-level rubric and two AERA essay prompts of roughly 1,200-1,400 responses on four-point rubrics.
  arXiv  Detail & Related papers  (2026-09-08T14:26:19Z)
• Divergent large language model predictions from convergent representations in ambiguous word pairs [2.4087148947930634]
  We investigate how decoder-only transformers resolve lexical ambiguity through layer-by-layer analysis.<n>For both homonyms and polysemes, we find that representations become maximally distinct in middle layers, then partially reconverge in late layers.
  arXiv  Detail & Related papers  (2026-08-03T07:26:45Z)
• Architecture-Aware Explanation Auditing for Industrial Visual Inspection [1.3054033103300278]
  This paper operationalizes an architecture-aware explanation audit protocol grounded in the native-readout hypothesis.<n>On WM-811K wafer maps (9 classes, 172k images) under a three-seed zero-fill perturbation protocol, ViT-Tiny + Attention Rollout attains Deletion AUC 0.211 against 0.432-0.525 for Swin-Tiny.
  arXiv  Detail & Related papers  (2026-05-14T01:48:00Z)
• Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale [40.31924374728614]
  The Platonic Representation Hypothesis suggests that neural networks trained on different modalities align and eventually converge toward the same representation of reality.<n>We show that the experimental evidence for this hypothesis is fragile and depends critically on the evaluation regime.
  arXiv  Detail & Related papers  (2026-04-20T17:56:02Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• Gauge-invariant representation holonomy [1.078600700827543]
  Deep networks learn internal representations whose geometry--how features bend, rotate, and evolve--affects both generalization and robustness.<n>Existing similarity measures such as CKA or SVCCA capture pointwise overlap between activation sets, but miss how representations change along input paths.<n>We introduce representation holonomy, a gauge-invariant statistic that measures this path dependence.
  arXiv  Detail & Related papers  (2026-01-29T12:51:17Z)
• Test-time Verification via Optimal Transport: Coverage, ROC, & Sub-optimality [53.03186946689658]
  Test-time scaling with verification has shown promise in improving the performance of large language models.<n>The effect of verification manifests through interactions of three quantities: (i) the generator's coverage, (ii) the verifier's region of convergence (ROC), and (iii) the sampling algorithm's sub-optimality.<n>We frame verifiable test-time scaling as a transport problem. This characterizes the interaction of coverage, ROC, and sub-optimality.
  arXiv  Detail & Related papers  (2025-10-21T18:05:42Z)
• Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks [50.2033914945157]
  We present a representation learning framework, Intensity Profile Projection, for continuous-time dynamic network data. The framework consists of three stages: estimating pairwise intensity functions, learning a projection which minimises a notion of intensity reconstruction error. Moreoever, we develop estimation theory providing tight control on the error of any estimated trajectory, indicating that the representations could even be used in quite noise-sensitive follow-on analyses.
  arXiv  Detail & Related papers  (2023-06-09T15:38:25Z)
• Linear Connectivity Reveals Generalization Strategies [54.947772002394736]
  Some pairs of finetuned models have large barriers of increasing loss on the linear paths between them. We find distinct clusters of models which are linearly connected on the test loss surface, but are disconnected from models outside the cluster. Our work demonstrates how the geometry of the loss surface can guide models towards different functions.
  arXiv  Detail & Related papers  (2022-05-24T23:43:02Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)
• Spatially relaxed inference on high-dimensional linear models [48.989769153211995]
  We study the properties of ensembled clustered inference algorithms which combine spatially constrained clustering, statistical inference, and ensembling to aggregate several clustered inference solutions. We show that ensembled clustered inference algorithms control the $delta$-FWER under standard assumptions for $delta$ equal to the largest cluster diameter.
  arXiv  Detail & Related papers  (2021-06-04T16:37:19Z)
• Finding Geometric Models by Clustering in the Consensus Space [61.65661010039768]
  We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects.
  arXiv  Detail & Related papers  (2021-03-25T14:35:07Z)

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.