It's All in The [MASK]: Simple Instruction-Tuning Enables BERT-like Masked Language Models As Generative Classifiers

• URL: http://arxiv.org/abs/2502.03793v2
• Date: Mon, 10 Feb 2025 14:08:19 GMT
• Title: It's All in The [MASK]: Simple Instruction-Tuning Enables BERT-like Masked Language Models As Generative Classifiers
• Authors: Benjamin Clavié, Nathan Cooper, Benjamin Warner,
• Abstract summary: We introduce ModernBERT-Large-Instruct, a encoder model that leverages its masked language modelling head for generative classification.<n>Our approach employs an intentionally simple training loop and inference mechanism that requires no heavy pre-processing.<n>ModernBERT-Large-Instruct exhibits strong zero-shot performance on both classification and knowledge-based tasks.
• Score: 2.3923290791822267
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While encoder-only models such as BERT and ModernBERT are ubiquitous in real-world NLP applications, their conventional reliance on task-specific classification heads can limit their applicability compared to decoder-based large language models (LLMs). In this work, we introduce ModernBERT-Large-Instruct, a 0.4B-parameter encoder model that leverages its masked language modelling (MLM) head for generative classification. Our approach employs an intentionally simple training loop and inference mechanism that requires no heavy pre-processing, heavily engineered prompting, or architectural modifications. ModernBERT-Large-Instruct exhibits strong zero-shot performance on both classification and knowledge-based tasks, outperforming similarly sized LLMs on MMLU and achieving 93% of Llama3-1B's MMLU performance with 60% less parameters. We also demonstrate that, when fine-tuned, the generative approach using the MLM head matches or even surpasses traditional classification-head methods across diverse NLU tasks.This capability emerges specifically in models trained on contemporary, diverse data mixes, with models trained on lower volume, less-diverse data yielding considerably weaker performance. Although preliminary, these results demonstrate the potential of using the original generative masked language modelling head over traditional task-specific heads for downstream tasks. Our work suggests that further exploration into this area is warranted, highlighting many avenues for future improvements.

Related papers

• Should We Still Pretrain Encoders with Masked Language Modeling? [27.19054714197245]
  Recent evidence suggests that decoder models pretrained with Causal Language Modeling (CLM) can be effectively repurposed as encoders.<n>We train a total of 38 models ranging from 210 million to 1 billion parameters, and conduct over 15,000 fine-tuning and evaluation runs.<n>We find that while training with high-level CLM yields better performance across text representation tasks, CLM-trained models are more data-efficient and demonstrate improved fine-tuning stability.
  arXiv  Detail & Related papers  (2025-07-01T17:45:48Z)
• Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? [13.077853383476974]
  This study challenges the prevailing "LLM-centric" trend by systematically comparing three category methods.<n>Our findings reveal that BERT-like models often outperform LLMs.<n>We propose TaMAS, a fine-grained task selection strategy, advocating for a nuanced, task-driven approach over a one-size-fits-all reliance on LLMs.
  arXiv  Detail & Related papers  (2025-05-23T05:46:42Z)
• Learnware of Language Models: Specialized Small Language Models Can Do Big [50.285859986475394]
  This paper presents a preliminary attempt to apply the learnware paradigm to language models.<n>We simulated a learnware system comprising approximately 100 learnwares of specialized SLMs with 8B parameters.<n>By selecting one suitable learnware for each task-specific inference, the system outperforms the base SLMs on all benchmarks.
  arXiv  Detail & Related papers  (2025-05-19T17:54:35Z)
• Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks [0.0]
  Large Language Models (LLMs) have significantly advanced Natural Language Processing (NLP) This study evaluates the continual fine-tuning of various open-source LLMs on key NLU tasks. Our results indicate that models such as Phi-3.5-mini exhibit minimal forgetting while maintaining strong learning capabilities.
  arXiv  Detail & Related papers  (2025-04-01T23:06:55Z)
• Instruction-Following Pruning for Large Language Models [58.329978053711024]
  We move beyond the traditional static pruning approach of determining a fixed pruning mask for a model.<n>In our method, the pruning mask is input-dependent and adapts dynamically based on the information described in a user instruction.<n>Our approach, termed "instruction-following pruning", introduces a sparse mask predictor that takes the user instruction as input and dynamically selects the most relevant model parameters for the given task.
  arXiv  Detail & Related papers  (2025-01-03T20:19:14Z)
• KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model [27.25688303240741]
  KaLM-Embedding is a general multilingual embedding model that leverages a large quantity of cleaner, more diverse, and domain-specific training data.<n>Our model has been trained with key techniques proven to enhance performance.
  arXiv  Detail & Related papers  (2025-01-02T03:17:51Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity Recognition [3.4923338594757674]
  Large language models (LLMs) can be used to train a model capable of extracting various types of entities. In this paper, we utilize the open-sourced LLM LLaMA2 as the backbone model, and design specific instructions to distinguish between different types of entities and datasets. Our model VANER, trained with a small partition of parameters, significantly outperforms previous LLMs-based models and, for the first time, as a model based on LLM, surpasses the majority of conventional state-of-the-art BioNER systems.
  arXiv  Detail & Related papers  (2024-04-27T09:00:39Z)
• LLM Augmented LLMs: Expanding Capabilities through Composition [56.40953749310957]
  CALM -- Composition to Augment Language Models -- introduces cross-attention between models to compose their representations and enable new capabilities. We illustrate that augmenting PaLM2-S with a smaller model trained on low-resource languages results in an absolute improvement of up to 13% on tasks like translation into English. When PaLM2-S is augmented with a code-specific model, we see a relative improvement of 40% over the base model for code generation and explanation tasks.
  arXiv  Detail & Related papers  (2024-01-04T18:53:01Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation [68.30497162547768]
  We propose MoEBERT, which uses a Mixture-of-Experts structure to increase model capacity and inference speed. We validate the efficiency and effectiveness of MoEBERT on natural language understanding and question answering tasks.
  arXiv  Detail & Related papers  (2022-04-15T23:19:37Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)

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.