Mixture-of-Experts (MoE) is a cornerstone for scaling LLMs, yet its training dynamics remain poorly understood, often leading to sub-optimal specialization. Moving beyond static routing, we present a systematic study of the MoE lifecycle using Helmholtz Free Energyand Router Entropy. We identify a universal Three-Stage Phase Transition—Exploration, Symmetry Breaking, and Stabilization—marked by an Energy Climb and Plateau. This reflects Frustrated Exploration, caused by structural interference between specialization drives and uniformity constraints. To address this, we propose Uncertainty-Aware Routing (UAR), which aligns routing with the model’s epistemic state via: (1) Evidence-Triggered Expansion, increasing active experts for high-energy tokens, and (2) Epistemic Masking, applying load-balancing only in high-uncertainty regimes to shield mature experts. Experiments confirm UAR reduces perplexity and improves expert distinctiveness, offering a principled path toward thermodynamically aligned computation.

Existing approaches to increasing the effective depth of Transformers predominantly rely on parameter reuse, extending computation through recursive execution.Under this paradigm, the network structure remains static along the training timeline, and additional computational depth is uniformly assigned to entire blocks at the parameter level.This rigidity across training time and parameter space leads to substantial computational redundancy during training.In contrast, we argue that depth allocation during training should not be a static preset, but rather a progressively growing structural process. Our systematic analysis reveals a deep-to-shallow maturation trajectory across layers, where high-entropy attention heads play a crucial role in semantic integration. Motivated by this observation, we introduce the Sparse Growing Transformer (SGT).SGT is a training-time sparse depth allocation framework that progressively extends recurrence from deeper to shallower layers via targeted attention looping on informative heads. This mechanism induces structural sparsity by selectively increasing depth only for a small subset of parameters as training evolves.Extensive experiments across multiple parameter scales demonstrate that SGT consistently outperforms training-time static block-level looping baselines under comparable settings, while reducing the additional training FLOPs overhead from approximately 16–20% to only 1–3% relative to a standard Transformer backbone.

Large language models (LLMs) face inherent performance bottlenecks under parameter constraints, particularly in processing critical tokens that demand complex reasoning. Empirical analysis reveals challenging tokens induce abrupt gradient spikes across layers, exposing architectural stress points in standard Transformers. Building on this insight, we propose Inner Thinking Transformer (ITT), which reimagines layer computations as implicit thinking steps. ITT dynamically allocates computation through Adaptive Token Routing, iteratively refines representations via Residual Thinking Connections, and distinguishes reasoning phases using Thinking Step Encoding. ITT enables deeper processing of critical tokens without parameter expansion. Evaluations across 162M-466M parameter models show ITT achieves 96.5% performance of a 466M Transformer using only 162M parameters, reduces training data by 43.2%, and outperforms Transformer/Loop variants in 11 benchmarks. By enabling elastic computation allocation during inference, ITT balances performance and efficiency through architecture-aware optimization of implicit thinking pathways.

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the extensive memory consumption of KV Cache involving long-context modeling. Despite several works proposing to evict unnecessary tokens from the KV Cache, most of them rely on the biased local statistics of accumulated attention scores and report performance using unconvincing metric like perplexity on inadequate short-text evaluation. In this paper, we propose NACL, a general framework for long-context KV cache eviction that achieves more optimal and efficient eviction in a single operation during the encoding phase. Due to NACL’s efficiency, we combine more accurate attention score statistics in Proxy-Tokens Eviction with the diversified random eviction strategy of Random Eviction, aiming to alleviate the issue of attention bias and enhance the robustness in maintaining pivotal tokens for long-context modeling tasks. Notably, our method significantly improves the performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 5× with over 95% performance maintenance. Code available at https://github.com/PaddlePaddle/Research/tree/master/NLP/ACL2024-NACL.

In the new era of language models, small models (with billions of parameter sizes) are receiving increasing attention due to their flexibility and cost-effectiveness in deployment. However, limited by the model size, the performance of small models trained from scratch may often be unsatisfactory. Learning a stronger and smaller model with the help of larger models is an intuitive idea. Inspired by the observing modular structures in preliminary analysis, we propose LEMON to learn competent initial points for smaller models by fusing parameters from larger models, thereby laying a solid foundation for subsequent training. Specifically, the parameter fusion process involves two operators for layer and dimension, respectively, and we also introduce controllable receptive fields to model the prior parameter characteristics. In this way, the larger model could be transformed into any specific smaller scale and architecture. Starting from LLaMA 2-7B, we revive two stronger and smaller models with 1.3B and 2.7B. Experimental results demonstrate that the fusion-based method exhibits flexibility and outperforms a series of competitive baselines in terms of both effectiveness and efficiency.

This paper describes our winning system on SemEval 2022 Task 7: Identifying Plausible Clarifications ofImplicit and Underspecified Phrases in Instructional Texts. A replaced token detection pre-trained model is utilized with minorly different task-specific heads for SubTask-A: Multi-class Classification and SubTask-B: Ranking. Incorporating a pattern-aware ensemble method, our system achieves a 68.90% accuracy score and 0.8070 spearman’s rank correlation score surpassing the 2nd place with a large margin by 2.7 and 2.2 percent points for SubTask-A and SubTask-B, respectively. Our approach is simple and easy to implement, and we conducted ablation studies and qualitative and quantitative analyses for the working strategies used in our system.

Transformers are not suited for processing long documents, due to their quadratically increasing memory and time consumption. Simply truncating a long document or applying the sparse attention mechanism will incur the context fragmentation problem or lead to an inferior modeling capability against comparable model sizes. In this paper, we propose ERNIE-Doc, a document-level language pretraining model based on Recurrence Transformers. Two well-designed techniques, namely the retrospective feed mechanism and the enhanced recurrence mechanism, enable ERNIE-Doc, which has a much longer effective context length, to capture the contextual information of a complete document. We pretrain ERNIE-Doc to explicitly learn the relationships among segments with an additional document-aware segment-reordering objective. Various experiments were conducted on both English and Chinese document-level tasks. ERNIE-Doc improved the state-of-the-art language modeling result of perplexity to 16.8 on WikiText-103. Moreover, it outperformed competitive pretraining models by a large margin on most language understanding tasks, such as text classification and question answering.