Know Your Limits: Entropy Estimation Modeling for Compression and Generalization

• URL: http://arxiv.org/abs/2511.10618v1
• Date: Fri, 14 Nov 2025 02:00:12 GMT
• Title: Know Your Limits: Entropy Estimation Modeling for Compression and Generalization
• Authors: Benjamin L. Badger, Matthew Neligeorge,
• Abstract summary: We introduce encoder-augmented causal decoder model architectures that exhibit superior training efficiency characteristics.<n>We show that causal models trained to approach but not exceed estimated per-token entropies exhibit greater generalization than models trained without taking entropy into account.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language prediction is constrained by informational entropy intrinsic to language, such that there exists a limit to how accurate any language model can become and equivalently a lower bound to language compression. The most efficient language compression algorithms today are causal (next token prediction) large language models, but the use of these models to form accurate estimates of language entropy is currently computationally infeasible. We introduce encoder-augmented causal decoder model architectures that exhibit superior training efficiency characteristics and achieve higher compression than causal transformers even when trained on modest hardware. We demonstrate how entropy estimates can be obtained on a per-token basis, and show that the generalization of models trained to approach the entropy of their training data necessarily exceeds the generalization of models trained to minimize loss beyond this value. We show empirically that causal models trained to approach but not exceed estimated per-token entropies exhibit greater generalization than models trained without taking entropy into account.

Related papers

• Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models [56.032091696552094]
  Generalization in natural data domains is progressively achieved during training before the onset of memorization.<n>Generalization vs. memorization is then best understood as a competition between time scales.<n>We show that this phenomenology is recovered in diffusion models learning a simple probabilistic context-free grammar with random rules.
  arXiv  Detail & Related papers  (2025-05-22T17:40:08Z)
• 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)
• Strong Model Collapse [16.071600606637908]
  We consider a supervised regression setting and establish the existance of a strong form of the model collapse phenomenon. Our results show that even the smallest fraction of synthetic data can lead to model collapse. We investigate whether increasing model size, an approach aligned with current trends in training large language models, exacerbates or mitigates model collapse.
  arXiv  Detail & Related papers  (2024-10-07T08:54:23Z)
• Observational Scaling Laws and the Predictability of Language Model Performance [51.2336010244645]
  We propose an observational approach that bypasses model training and instead builds scaling laws from 100 publically available models. We show that several emergent phenomena follow a smooth, sigmoidal behavior and are predictable from small models. We show how to predict the impact of post-training interventions like Chain-of-Thought and Self-Consistency as language model capabilities continue to improve.
  arXiv  Detail & Related papers  (2024-05-17T17:49:44Z)
• Non-Vacuous Generalization Bounds for Large Language Models [78.42762571499061]
  We provide the first non-vacuous generalization bounds for pretrained large language models. We show that larger models have better generalization bounds and are more compressible than smaller models.
  arXiv  Detail & Related papers  (2023-12-28T17:58:42Z)
• MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models [40.992566245706996]
  We propose a MiLe Loss function for mitigating the bias of learning difficulties with tokens. We train generative language models at different scales of 468M, 1.2B, and 6.7B parameters. Experiments reveal that models incorporating the proposed MiLe Loss can gain consistent performance improvement on downstream benchmarks.
  arXiv  Detail & Related papers  (2023-10-30T13:33:21Z)
• Training Trajectories of Language Models Across Scales [99.38721327771208]
  Scaling up language models has led to unprecedented performance gains. How do language models of different sizes learn during pre-training? Why do larger language models demonstrate more desirable behaviors?
  arXiv  Detail & Related papers  (2022-12-19T19:16:29Z)
• A Natural Bias for Language Generation Models [31.44752136404971]
  We show that we can endow standard neural language generation models with a separate module that reflects unigram frequency statistics as prior knowledge. We use neural machine translation as a test bed for this simple technique and observe that it: (i) improves learning efficiency; (ii) achieves better overall performance; and perhaps most importantly: appears to disentangle strong frequency effects.
  arXiv  Detail & Related papers  (2022-12-19T18:14:36Z)
• Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models [46.24479693469042]
  This paper shows that 1) pre-training loss cannot fully explain downstream performance and 2) flatness of the model is well-correlated with downstream performance where pre-training loss is not.
  arXiv  Detail & Related papers  (2022-10-25T17:45:36Z)
• Quark: Controllable Text Generation with Reinforced Unlearning [68.07749519374089]
  Large-scale language models often learn behaviors that are misaligned with user expectations. We introduce Quantized Reward Konditioning (Quark), an algorithm for optimizing a reward function that quantifies an (un)wanted property. For unlearning toxicity, negative sentiment, and repetition, our experiments show that Quark outperforms both strong baselines and state-of-the-art reinforcement learning methods.
  arXiv  Detail & Related papers  (2022-05-26T21:11:51Z)

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.