Is there "Secret Sauce'' in Large Language Model Development?

• URL: http://arxiv.org/abs/2602.07238v1
• Date: Fri, 06 Feb 2026 22:32:31 GMT
• Title: Is there "Secret Sauce'' in Large Language Model Development?
• Authors: Matthias Mertens, Natalia Fischl-Lanzoni, Neil Thompson,
• Abstract summary: Using training and benchmark data for 809 models released between 2022 and 2025, we estimate scaling-law regressions with release-date and developer fixed effects.<n>We find clear evidence of developer-specific efficiency advantages, but their importance depends on where models lie in the performance distribution.
• Score: 1.6725669564247125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Do leading LLM developers possess a proprietary ``secret sauce'', or is LLM performance driven by scaling up compute? Using training and benchmark data for 809 models released between 2022 and 2025, we estimate scaling-law regressions with release-date and developer fixed effects. We find clear evidence of developer-specific efficiency advantages, but their importance depends on where models lie in the performance distribution. At the frontier, 80-90% of performance differences are explained by higher training compute, implying that scale--not proprietary technology--drives frontier advances. Away from the frontier, however, proprietary techniques and shared algorithmic progress substantially reduce the compute required to reach fixed capability thresholds. Some companies can systematically produce smaller models more efficiently. Strikingly, we also find substantial variation of model efficiency within companies; a firm can train two models with more than 40x compute efficiency difference. We also discuss the implications for AI leadership and capability diffusion.

Related papers

• DEPO: Dual-Efficiency Preference Optimization for LLM Agents [75.6723341304463]
  We propose DEPO, a dual-efficiency preference optimization method that jointly rewards succinct responses and fewer action steps.<n>Experiments on WebShop and BabyAI show that DEPO cuts token usage by up to 60.9% and steps by up to 26.9%, while achieving up to a 29.3% improvement in performance.
  arXiv  Detail & Related papers  (2025-11-19T12:38:43Z)
• Revealing the Power of Post-Training for Small Language Models via Knowledge Distillation [43.68215777330875]
  We introduce a systematic post-training pipeline that efficiently enhances small model accuracy.<n>The resulting instruction-tuned model achieves state-of-the-art performance.<n>This work provides a practical and efficient solution for developing high-performance language models on Ascend edge devices.
  arXiv  Detail & Related papers  (2025-09-30T16:40:55Z)
• Compute-Optimal Scaling for Value-Based Deep RL [99.680827753493]
  We investigate compute scaling for online, value-based deep RL.<n>Our analysis reveals a nuanced interplay between model size, batch size, and UTD.<n>We provide a mental model for understanding this phenomenon and build guidelines for choosing batch size and UTD.
  arXiv  Detail & Related papers  (2025-08-20T17:54:21Z)
• Meek Models Shall Inherit the Earth [1.9647223141071104]
  The past decade has seen incredible scaling of AI systems by a few companies, leading to inequality in AI model performance.<n>This paper argues that, contrary to prevailing intuition, the diminishing returns to compute scaling will lead to a convergence of AI model capabilities.
  arXiv  Detail & Related papers  (2025-07-10T17:10:07Z)
• Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs [96.68469559192846]
  We present two differently sized MoE large language models (LLMs)<n>Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters.<n>We propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency.
  arXiv  Detail & Related papers  (2025-03-07T04:43:39Z)
• Streaming Looking Ahead with Token-level Self-reward [50.699168440048716]
  We propose a policy model with token-level self-reward modeling (TRM) capability to eliminate the need for external models and extra communication.<n>In addition, we propose a streaming-looking-ahead (SLA) algorithm to further boost search efficiency with better parallelization.<n>If we combine SLA with reinforcement fine-tuning techniques such as DPO, SLA achieves an overall win rate of 89.4%.
  arXiv  Detail & Related papers  (2025-02-24T22:35:53Z)
• Entropy Adaptive Decoding: Dynamic Model Switching for Efficient Inference [0.0]
  We present Entropy Adaptive Decoding (EAD), a novel approach for efficient language model inference.<n>EAD switches between different-sized models based on prediction uncertainty.<n>We show remarkable efficiency gains across different model families.
  arXiv  Detail & Related papers  (2025-02-05T22:15:21Z)
• Linear Discriminant Analysis in Credit Scoring: A Transparent Hybrid Model Approach [9.88281854509076]
  We implement Linear Discriminant Analysis (LDA) as a feature reduction technique, which reduces the burden of the models complexity.<n>Our hybrid model, XG-DNN, outperformed other models with the highest accuracy of 99.45% and a 99% F1 score with LDA.<n>To interpret model decisions, we have applied 2 different explainable AI techniques named LIME (local) and Morris Sensitivity Analysis (global)
  arXiv  Detail & Related papers  (2024-12-05T14:21:18Z)
• QuAKE: Speeding up Model Inference Using Quick and Approximate Kernels for Exponential Non-Linearities [13.051302134031802]
  QuAKE is a collection of operators that leverage certain properties of IEEE-754 floating point representations to quickly approximate the exponential function.<n>We propose optimizations that enhance the efficiency of QuAKE in commonly used exponential non-linearities such as Softmax, GELU, and the Logistic function.
  arXiv  Detail & Related papers  (2024-11-30T09:26:56Z)
• Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes [91.58845026796149]
  We introduce Distilling step-by-step, a new mechanism that trains small models that outperform large language models. We present three findings across 4 NLP benchmarks.
  arXiv  Detail & Related papers  (2023-05-03T17:50:56Z)
• Towards Compute-Optimal Transfer Learning [82.88829463290041]
  We argue that zero-shot structured pruning of pretrained models allows them to increase compute efficiency with minimal reduction in performance. Our results show that pruning convolutional filters of pretrained models can lead to more than 20% performance improvement in low computational regimes.
  arXiv  Detail & Related papers  (2023-04-25T21:49:09Z)
• Towards Practical Lipreading with Distilled and Efficient Models [57.41253104365274]
  Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. There is still a significant gap between the current methodologies and the requirements for an effective deployment of lipreading in practical scenarios. We propose a series of innovations that significantly bridge that gap: first, we raise the state-of-the-art performance by a wide margin on LRW and LRW-1000 to 88.5% and 46.6%, respectively using self-distillation.
  arXiv  Detail & Related papers  (2020-07-13T16:56:27Z)

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.