Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark

• URL: http://arxiv.org/abs/2604.03589v1
• Date: Sat, 04 Apr 2026 04:35:20 GMT
• Title: Entropy and Attention Dynamics in Small Language Models: A Trace-Level Structural Analysis on the TruthfulQA Benchmark
• Abstract summary: Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings.<n>Current evaluation methodology relies on final accuracy or hallucination rates without explaining how internal model behavior affects outputs.<n>This study introduces a trace-level analysis of entropy and attention dynamics in SLMs evaluated with the TruthfulQA dataset.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Small language models (SLMs) have been increasingly deployed in edge devices and other resource-constrained settings. However, these models make confident mispredictions and produce unstable output, making them risky for factual and decision-critical tasks. Current evaluation methodology relies on final accuracy or hallucination rates without explaining how internal model behavior affects outputs. Specifically, how entropy evolves during decoding, how attention is distributed across layers, and how hidden representations contribute to uncertainty, logical inconsistencies, and misinformation propagation are often overlooked. Consequently, this study introduces a trace-level analysis of entropy and attention dynamics in SLMs evaluated with the TruthfulQA dataset. Four models with parameter ranges of 1B-1.7B parameters were examined via token-level output entropy, attention entropy, head dispersion, and hidden-state representation. The results reflect three model classifications by entropy patterns. Deterministic models (DeepSeek-1.5B and LLaMA-1B): output entropy decreases over time. Exploratory models (Gemma-1B): with increasing entropy, and balanced models (Qwen-1.7B): have moderate and stable entropy. Also, each group has distinctively different hidden-state movement and attention dispersion patterns. The analysis demonstrates that truthfulness in SLMs emerges from structured entropy and attention dynamics. Monitoring and optimizing these internal uncertainty patterns can guide the design of a more reliable, hallucination-aware, and application-specific edge SLMs.

Related papers

• Emergent Latent-State Computation under Stochastic Volatility [3.8881341075549947]
  We study how models internally represent latent dynamics under noisy, partially observed observations.<n>Across architectures, losses, and output heads, we find evidence for a two-stage computation.<n>These results suggest that volatility models provide a useful benchmark for interpretability under noisy latent dynamics and partial observability.
  arXiv  Detail & Related papers  (2026-07-28T08:49:48Z)
• Learning Uncertainty from Sequential Internal Dispersion in Large Language Models [52.29267172760918]
  Uncertainty estimation is a promising approach to detect hallucinations in large language models.<n>Recent approaches commonly depend on model internal states to estimate uncertainty.<n>We present Sequential Internal Variance Representation (SIVR), a supervised hallucination detection framework.
  arXiv  Detail & Related papers  (2026-04-17T06:31:29Z)
• Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory [0.0]
  This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency.<n>By analyzing the eigenvalue dynamics of hidden activations across layers and inputs, this work shows that spectral statistics provide a compact, stable, and interpretable lens on model behavior.<n>Within this framework, the first contribution, EigenTrack, introduces a real-time method for detecting hallucinations and out-of-distribution behavior in large language and vision-language models.<n>The second contribution, RMT-KD, presents a principled approach to compressing deep networks via random matrix theoretic knowledge distillation.
  arXiv  Detail & Related papers  (2026-02-25T19:11:56Z)
• Same Answer, Different Representations: Hidden instability in VLMs [65.36933543377346]
  We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness.<n>We apply this framework to modern Vision Language Models (VLMs) across the SEEDBench, MMMU, and POPE datasets.
  arXiv  Detail & Related papers  (2026-02-06T12:24:26Z)
• EDIS: Diagnosing LLM Reasoning via Entropy Dynamics [3.858418431840288]
  We show that the emphtemporal evolution of confidence during generation carries richer information than aggregate statistics alone.<n>We introduce the Entropy Dynamics Instability Score (textbfEDIS), a trajectory-level metric quantifying instability in entropy evolution.
  arXiv  Detail & Related papers  (2026-02-01T15:43:50Z)
• Explaining Machine Learning Predictive Models through Conditional Expectation Methods [0.0]
  MUCE is a model-agnostic method for local explainability designed to capture prediction changes from feature interactions.<n>Two quantitative indices, stability and uncertainty, summarize local behavior and assess model reliability.<n>Results show that MUCE effectively captures complex local model behavior, while the stability and uncertainty indices provide meaningful insight into prediction confidence.
  arXiv  Detail & Related papers  (2026-01-12T08:34:36Z)
• Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models [77.55829017952728]
  EntPruner is an entropy-guided automatic progressive pruning framework for diffusion and flow models.<n>Experiments on DiT and SiT models demonstrate the effectiveness of EntPruner, achieving up to 2.22$times$ inference speedup.
  arXiv  Detail & Related papers  (2025-11-26T07:20:48Z)
• Entropy-Based Block Pruning for Efficient Large Language Models [81.18339597023187]
  We propose an entropy-based pruning strategy to enhance efficiency while maintaining performance.<n> Empirical analysis reveals that the entropy of hidden representations decreases in the early blocks but progressively increases across most subsequent blocks.
  arXiv  Detail & Related papers  (2025-04-04T03:42:34Z)
• Spatial Reasoning with Denoising Models [49.83744014336816]
  We introduce a framework to perform reasoning over sets of continuous variables via denoising generative models.<n>For the first time, that order of generation can successfully be predicted by the denoising network itself.<n>Using these findings, we can increase the accuracy of specific reasoning tasks from 1% to >50%.
  arXiv  Detail & Related papers  (2025-02-28T14:08:30Z)
• Quantifying Semantic Emergence in Language Models [31.608080868988825]
  Large language models (LLMs) are widely recognized for their exceptional capacity to capture semantics meaning.<n>In this work, we introduce a quantitative metric, Information Emergence (IE), designed to measure LLMs' ability to extract semantics from input tokens.
  arXiv  Detail & Related papers  (2024-05-21T09:12:20Z)
• Neural Superstatistics for Bayesian Estimation of Dynamic Cognitive Models [2.7391842773173334]
  We develop a simulation-based deep learning method for Bayesian inference, which can recover both time-varying and time-invariant parameters. Our results show that the deep learning approach is very efficient in capturing the temporal dynamics of the model.
  arXiv  Detail & Related papers  (2022-11-23T17:42:53Z)
• Understanding Neural Abstractive Summarization Models via Uncertainty [54.37665950633147]
  seq2seq abstractive summarization models generate text in a free-form manner. We study the entropy, or uncertainty, of the model's token-level predictions. We show that uncertainty is a useful perspective for analyzing summarization and text generation models more broadly.
  arXiv  Detail & Related papers  (2020-10-15T16:57:27Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)

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.