Related papers: DEMix Layers: Disentangling Domains for Modular La…
Domain-specific adaptation is critical to maximizing the performance of pre-trained language models (PLMs) on one or multiple targeted tasks, especially under resource-constrained use cases, such as edge devices. However, existing methods…
Detecting machine-generated text (MGT) has emerged as a critical challenge, driven by the rapid advancement of large language models (LLMs) capable of producing highly realistic, human-like content. However, the performance of current…
Model merging, which combines multiple domain-specialized experts into a single model, offers a practical path to endow Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) with broad capabilities without the cost of…
In this work, we propose a method that combines two popular research areas by injecting linguistic structures into pre-trained language models in the parameter-efficient fine-tuning (PEFT) setting. In our approach, parallel adapter modules…
We introduce LM-Lexicon, an innovative definition modeling approach that incorporates data clustering, semantic expert learning, and model merging using a sparse mixture-of-experts architecture. By decomposing the definition modeling task…
Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter…
Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in…
Mixture-of-Experts (MoE) language models organize knowledge into explicitly routed expert modules, making expert-level representations traceable and analyzable. By analyzing expert activation patterns in MoE large language models (LLMs), we…
We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…
Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for training and final-layer representations for predictions, potentially overlooking the predictive power embedded in intermediate layers. Surprisingly,…
Mixture-of-Experts (MoE) architectures have emerged as a promising approach to scale Large Language Models (LLMs). MoE boosts the efficiency by activating a subset of experts per token. Recent works show that fine-grained experts…
Determining an effective data mixture is a key factor in Large Language Model (LLM) pre-training, where models must balance general competence with proficiency on hard tasks such as math and code. However, identifying an optimal mixture…
Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is…
Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time reasoning to multi-model collaboration. We study language model networks, where pre-trained language…
The curse of multilinguality phenomenon is a fundamental problem of multilingual Large Language Models (LLMs), where the competition between massive languages results in inferior performance. It mainly comes from limited capacity and…
Extending a fully post-trained language model with new domain capabilities is fundamentally limited by monolithic training paradigms: retraining from scratch is expensive and scales poorly, while continued training often degrades existing…
Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and require retraining when new data is introduced. To this end, we…
In the era of Large Language Models (LLMs), the Mixture of Experts (MoE) architecture has emerged as an effective approach for training extremely large models with improved computational efficiency. This success builds upon extensive prior…
In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity…
Recent advancements in building domain-specific large language models (LLMs) have shown remarkable success, especially in tasks requiring reasoning abilities like logical inference over complex relationships and multi-step problem solving.…