Masked Language Modeling

Also known as MLM

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 26

Oct 6, 2026cs.CL

Tiny-Scale Chinese BERT Pretraining: A Controlled Comparison of MLM, WWM, and MacBERT Strategies

Pretraining strategies significantly impact the quality of language models, yet existing comparisons of Masked Language Modeling (MLM), Whole Word Masking (WWM), and MacBERT-style replacement have focused primarily on base-scale models (>=110M parameters). This paper presents a controlled comparison of these three strategies on a tiny-scale Chinese BERT model (4 layers, 256 hidden dimensions, 8.7M parameters). Under identical architecture, corpus (1.29M sentences from Chinese Wikipedia), and hyperparameters, we train three models from scratch and evaluate them across five intrinsic dimensions: perplexity, MLM hit rate, semantic discrimination, grammatical judgment, and contextual sensitivity. At tiny scale, MLM achieves the best overall intrinsic performance (winning 3 of 5 dimensions), while WWM excels in both perplexity (1.27 vs. 2.10, a 39.5% improvement) and MLM hit rate (22% vs. 16%). Notably, MacBERT under a severely limited synonym dictionary (222 entries, 3.3% coverage) exhibits severe perplexity degradation (47.23, 22x higher than MLM), yielding a ranking (MLM > WWM >> MacBERT) that differs markedly from the established base-scale conclusion (MacBERT > WWM > MLM). We further identify a critical evaluation pitfall: MacBERT achieves the lowest training loss (2.17) yet the highest perplexity (47.23), revealing that training loss alone is unreliable under mixed replacement strategies. All models and corpus are publicly available at https://huggingface.co/eebyp.

Yiping Bai

Guangdong Haiqixing Marine Technology Co., Ltd.

Language Model Pretraining Language Modeling Masked Language Modeling Small Language Models Transformer

Oct 1, 2026stat.ML

The hidden advantage of mask resampling: a theory of masked autoencoders

Why can masked prediction learn useful representations that unmasked reconstruction misses? We study this question in a high-dimensional model of a masked autoencoder (MAE) trained on data with shared latent structure and heterogeneous noise. We prove that masked linear reconstruction can recover the latent feature at linear sample complexity in regimes where unmasked linear reconstruction, equivalent to PCA, fails. The analysis also quantifies the statistical advantage of mask resampling, an established ingredient of masked pretraining. By introducing a fixed collection of

K

masks per sample, we characterize its effect on feature recovery and downstream performance, identifying regimes where greater mask diversity lowers sample complexity. Guided by this prediction, we find that random cropping and flipping in standard image-training pipelines can obscure the advantage of mask resampling by renewing the prediction task even when the patch mask is fixed. Removing these transformations reveals a downstream advantage for dynamic over static masking in CNN autoencoders and vision transformers. A complementary BERT pilot finds benefits from greater mask diversity on downstream language tasks. Our results separate the benefit of the masked prediction objective from that of mask diversity, and show how a tractable theory can guide experiments that uncover advantages hidden by standard training practices.

Jorge Medina Moreira, Lorenzo Bardone, Lenka Zdeborová

Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland

Masked Autoencoders Masked Language Modeling Self-Supervised Visual Representation Learning Masked Image Modeling

Sep 22, 2026cs.LG

GeoRVQ: Decoder-aware geometry for residual-token prediction in physiological signals

Residual vector quantization (RVQ) turns physiological waveforms into compact token sequences, but conventional masked modeling treats every incorrect token as equally costly. We propose GeoRVQ, a coarse-to-fine masked token model whose objective reflects the local response of a frozen waveform decoder. Decoder-induced costs define geometry-aware soft targets and expected distortion, while quantizer-causal prediction follows residual dependencies from coarse to fine levels. In a descriptive aggregate over MIMIC-IV Waveform, VitalDB, and CODE-15%, GeoRVQ increases exact token accuracy from

.133\pm.004

to

.143\pm.003

, reduces decoded distance from

.606\pm.006

to

.393\pm.007

, and increases R-peak F1 from

.784\pm.004

to

.837\pm.008

under matched model and training conditions. Across 45 held-out code substitutions, decoder-induced cost has a Spearman correlation of

.85

with realized decoded cost, compared with

.54

for Euclidean codeword distance. These results indicate that decoder-aware objectives can improve waveform and event preservation without requiring a large increase in exact token accuracy.

Bo Cui, Yaowen Zhang

Biomedical Signals and Systems, University of Twente, Enschede, The Netherlands

Masked Language Modeling Residual VQ

Sep 1, 2026cs.LG

Learning Task-Specific Antibody Representations via Function-Aware Masking

Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks. Yet, the corruption process itself is rarely leveraged as a source of inductive bias during pretraining. While preferentially masking complementarity-determining regions (CDRs) improves binding-related predictions, antibodies possess diverse biological priors over a variety of functions. Herein, we introduce function-aware masking, a family of pretraining algorithms that align mask placement with specific functional priors (e.g., from IMGT annotations or structure predictions) to shape the learned representation space. We show that these specialist masking strategies significantly improve performance on their respective objectives, yielding up to a 14% gain on structure-related tasks and up to a 5.9x improvement on CDR-related tasks. To further improve performance across multiple functional axes, we develop hybrid masking strategies that integrate multiple priors, balancing reconstruction over binding, structural, and biophysical objectives. Our results demonstrate that informed mask placement provides a parameter-free mechanism for imposing functional inductive biases in antibody language model training.

Ayan Goel, Thomas A. Walton, Amirali Aghazadeh

School of Computer Science, Georgia Institute of Technology · School of Electrical and Computer Engineering, Georgia Institute of Technology

Masked Language Modeling Protein Language Models Protein Representation Learning

Aug 8, 2026cs.CL

AraSSM: A bidirectional state-space encoder for Arabic masked language modeling

Pretrained Transformer encoders such as AraBERT, MARBERT, and CAMeLBERT have become the standard backbone for Arabic natural language understanding, but their self-attention mechanism scales quadratically with sequence length, which limits efficiency on long documents. Mamba, a selective state-space model (SSM), offers linear-time sequence modeling as a competitive alternative to attention, yet no dedicated bidirectional Mamba encoder pretrained specifically for Arabic currently exists. We introduce AraSSM, a bidirectional Mamba encoder pretrained via masked language modeling on a corpus combining Arabic Wikipedia and CulturaX text, trained end-to-end on four consumer-grade NVIDIA RTX 2080Ti GPUs (11GB) over approximately ten days. We evaluate AraSSM by fine-tuning on four established Arabic NLU benchmarks covering sentiment classification (HARD), named entity recognition (ANERcorp), extractive question answering (ARCD), and natural language inference (XNLI-ar), following the per-task evaluation protocol introduced by AraBERT, and report results as mean +/- standard deviation across three fine-tuning seeds. AraSSM matches or exceeds published base-sized Transformer baselines on sentiment classification (96.37 +/- 0.03% accuracy on HARD), is competitive on extractive QA (32.19 +/- 1.07 EM, 63.79 +/- 0.25 F1 on ARCD) and named entity recognition (81.54 +/- 0.30 entity-level F1 on ANERcorp), and trails the base-sized Transformer range on natural language inference (72.83 +/- 0.07% accuracy on XNLI-ar), despite being trained entirely from scratch on consumer hardware rather than large-scale accelerator clusters.

Ahmed Amine Aliane, Hassina Aliane, Nasredine Semmar

Arabic Institute for Translation, Algiers, Algeria · CERIST, Algeria · CEA LIST, Paris-Saclay, France

Language Model Pretraining Arabic NLP Masked Language Modeling State Space Models

Jul 30, 2026cs.LG

VESTIGE: A Knowledge-Guided Masking Strategy for Corruption-Aware Fine-Tuning of Genomic Transformers, Validated on Ancient DNA Reconstruction

Standard masked-language-model fine-tuning applies a uniform masking probability across every token position, assuming reconstruction difficulty is position-agnostic. When the degradation process is characterised and concentrated at predictable positions, this assumption fails: at peak damage sites the model can underperform a frequency-matched random predictor. We introduce VESTIGE, a parameter-free, drop-in replacement for the standard MLM collator that aligns the masking distribution with an empirically measured per-position corruption profile. We apply it to ancient DNA (aDNA) reconstruction, where cytosine deamination produces a position-dependent C-to-T / G-to-A gradient quantified per-position by mapDamage2. Rescaling so the mean C/G masking rate equals 15% - identical to standard MLM - isolates spatial redistribution as the sole variable, with model, data, seed, and hyperparameters held fixed across both DNABERT-2 runs on a mammoth CDS corpus (two specimens, seven genes). Across six terminal-zone widths and 626 paired windows, VESTIGE leads standard MLM at every width (Delta = +4.18 to +10.35 pp, all p < 10^-8), cuts validation cross-entropy by 13% (3.274 vs. 3.757), and yields ESMFold reconstructions with TM-score > 0.95 across all six reconstructions (three genes) even under damage amplified 10-30x beyond authentic PMD rates. A 1D CNN biosecurity classifier returns AUC = 0.935 and clears 98.2% of reconstructed windows, the 1.76% remainder attributable to reference-genome features, not reconstruction artefacts. The principle is domain-agnostic: any measurable position- or context-specific corruption profile - FFPE, bisulfite, metagenomic, or nanopore - substitutes directly for the PMD array, making VESTIGE a knowledge-guided training routine for intelligent systems operating on degraded or noisy sequence inputs.

Angshuman Chakravertty, Rahul Maheshwari

School of Technology Management & Engineering, SVKM’s Narsee Monjee Institute of Management Studies (NMIMS) Deemed-to-be-University, Jadcherla, Hyderabad 509301, Telangana, India, Hyderabad, India · School of Pharmacy and Technology Management, SVKM's Narsee Monjee Institute of Management Studies (NMIMS) Deemed-to-be-University, Hyderabad, Jadcheral-509301, Telangana, India · School of Pharmacy and Technology Management, SVKM's Narsee Monjee Institute of Management Studies (NMIMS) Deemed-to-University, Hyderabad, Jadcheral-509301, Telangana, India

Masked Language Modeling Language Modeling Genomics

Jul 26, 2026cs.CL

The JEPA Paradox in Language: The Geometry of Linguistic Alternatives

Joint-Embedding Predictive Architectures (JEPAs) are effective for images, video, and audio, yet deterministic JEPA-style latent prediction has not become a standard objective for text encoders. We argue that this gap reflects a mismatch between squared-error latent prediction and the conditional structure of language. The key requirement is conditional concentration: given a context and target location, the target representation should lie near a single meaningful point. Local image prediction often satisfies this through spatial continuity, whereas masked text can admit multiple valid token or span completions whose representations need not share a coherent center. We formalize this mismatch through three conditions---predictability, non-collapse, and low conditional variance---and show how their failure creates centroid degeneracy and collapse pressure in text. Matched I-JEPA and T-JEPA experiments reveal the predicted sequence: mutual-information saturation and elevated target variance precede train--validation instability, effective-rank degeneration, cosine collapse, and poor downstream transfer. The same pattern appears across five independent data seeds, indicating that it is not a sampling artifact. These results do not rule out predictive learning for language; they show that text-compatible JEPA objectives must preserve multiple plausible completions rather than compress them into a single latent point.

Anh Trac Duc Dinh, Khang Nhat Hoang Vo

Center for AI Research (CAIR), VinUniversity, Hanoi, Vietnam · Faculty of Computer Science and Engineering Ho Chi Minh City University of Technology (HCMUT), VNU-HCM Ho Chi Minh City, Vietnam · Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates

Representation Collapse Masked Language Modeling Joint-Embedding Predictive Architecture Predictive Representation Learning Representation Geometry in Language Models

Jul 14, 2026cs.AI

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

Coding agents must integrate external tool returns into ongoing reasoning - a capability that standard left-to-right pretraining on code exposes only in its forward direction. We observe that the action-observation-continuation loop of a coding agent is structurally isomorphic to a function call site, where a caller binds arguments, a callee returns a value computed elsewhere, and downstream code consumes that value. This conditioning structure exists at internet scale in ordinary code. We exploit it through function-aware fill-in-the-middle (FIM) mid-training: a self-supervised objective that masks functions selected via program dependency graph analysis and a complexity-inferability double criterion. We mid-train Qwen2.5-Coder-Instruct (7B/14B) and Qwen3-8B on a 2.6B-token decontaminated corpus drawn from 968 GitHub repositories, then apply existing agentic post-training pipelines. Mid-training improves SWE-Bench-Verified by +2.8/+3.0 at 7B/14B and by +3.2 on Qwen3-8B; SWE-Bench-Lite gains are +3.7/+4.0/+5.4 on the same models. The improvement holds across two post-training pipelines (R2E-Gym, SWE-Smith) and on a non-Qwen2.5 base (Qwen3-8B with SWE-Lego). Beyond in-domain gains, mid-training also mitigates the capability erosion that agentic post-training otherwise inflicts on non-agent coding (e.g., LiveCodeBench) and non-coding tool-use benchmarks (tau-bench, BFCL): although the mid-training corpus contains Python code only, the function-call inductive bias survives post-training and yields consistent gains.

Yubo Wang, Jiarong Liang, Yuxuan Zhang +5

University of Waterloo · 5Vector Institute · University of British Columbia +2

Masked Language Modeling Coding Agents Code Language Models LLM Training

Jul 5, 2026cs.LG

A Unified Framework for In-Context Learning with Causal and Masked Language Models

In-context learning (ICL) has emerged as a central capability of pretrained language models, yet its theoretical analysis has focused primarily on causal language models trained by left-to-right autoregressive prediction, such as GPT-style models. Masked language models instead recover masked tokens from bidirectional context, and their role in ICL remains less understood. We develop a statistical learning framework that represents the context examples by their empirical measure and models prediction as a function of the context and the query. This formulation places autoregressive and masked pretraining objectives within a common excess-risk analysis. Under Wasserstein-type regularity conditions, we relate pretraining with T tasks and N samples per task to k-shot excess risk at inference, obtaining same-order upper bounds for masked and autoregressive objectives. We also study task-distribution shift, where pretraining tasks are sampled from P and inference tasks from Q; the resulting bound contains an additional term controlled by the lifted Wasserstein distance between P and Q. The bounds further imply an order-optimal allocation under a fixed pretraining data budget and refined rates under intrinsic low-dimensional structure. Experiments on controlled function-learning tasks show that the Masked Pair Encoder (MPE) can achieve performance comparable to GPT-2-style causal Transformers, suggesting that ICL behavior is not specific to causal language models.

Chenrui Liu, Chuanlong Xie, Falong Tan +2

Beijing Normal University at Zhuhai Zhuhai, China · Hunan University Changsha, China · Sun Yat-sen University Shenzhen, China

Masked Language Modeling Autoregressive Language Modeling In-Context Learning Statistical Learning Theory

Jul 4, 2026cs.CL

Separating Representation from Reconstruction Enables Scalable Text Encoders

While decoders have rapidly scaled, encoders have remained largely unchanged since BERT. We revisit this disparity by frozen backbone evaluation via probing. Under this lens, the representations of BERT encoders become increasingly

\textit{unexploitable}

by frozen probes, despite improved perplexity. The misalignment originates in BERT's flat design, which couples representation learning to the token reconstruction loss. We propose

\textbf{CrossBERT}

, a two-part architecture that separates the learning of high-quality encoded representations from the rigid grounding of token reconstruction. This design further enables high masking ratios (

\ge 50\%

) and gradient collection over all tokens via a

\textit{Complementary Masking Strategy}

, respectively increasing throughput by

1.5

to

2\times

and sample efficiency by

2\times

. Overall, CrossBERT demonstrates monotonic scaling and superior performance on MTEB(eng, v2) and frozen GLUE benchmarks.

Megi Dervishi, Mathurin Videau, Yann LeCun

FAIR · 3New York University

Masked Language Modeling Self-Supervised Pre-Training Text Embedding Models

Jun 20, 2026cs.CL

Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining

Web data curation has been widely studied for decoder Large Language Model (LLM) pretraining. Encoders for dense-terminology domains such as medicine, by contrast, are pretrained on small, manually-curated corpora that limit scalability and writing style diversity, a bottleneck even more severe in non-English clinical settings. Whether web-scale data curation also benefits encoder Masked Language Modeling (MLM) in a dense-terminology domain remains an open question. To address this, we introduce two complementary levers. Medical-term density filtering selects documents rich in medical terms. Signal-amplifying rephrasing uses an LLM to rewrite documents into denser variants with broader entity contexts. We instantiate the recipe on French medical NLP. The medical-term density filter outperforms the widely-used educational quality filter on downstream medical tasks, and the two complement each other. Signal-amplifying rephrasing alone improves on raw web data, and mixing it with filtered web data produces the largest gain. The recipe yields FineMed, a French medical pretraining corpus, and DoctoBERT, a state-of-the-art French medical encoder family evaluated on both the public benchmark DrBenchmark and a proprietary clinical Named Entity Recognition (NER) task.

Bofeng Huang, Jacques Sun, Diane Bouchacourt +2

Doctolib · Work done while at Doctolib.

Language Model Pretraining Masked Language Modeling Training Data Curation Domain-Adaptive Pretraining Clinical NLP

Jun 17, 2026cs.IR

Rescaling MLM-Head for Neural Sparse Retrieval

Learned sparse retrieval (LSR) models such as SPLADE have traditionally used BERT-style masked language models as backbone encoders. A natural expectation is that replacing BERT with stronger pretrained encoders should improve retrieval effectiveness. However, we find that under standard SPLADE training recipes, backbones with large MLM-head L2 norms can suffer performance degradation and even training collapse under standard SPLADE training recipes. We identify this failure as a scale mismatch in the MLM head: SPLADE directly uses MLM-head outputs to construct sparse lexical representations, and query-document relevance is computed by an unnormalized dot product over these representations. As a result, an inflated MLM-head scale can amplify sparse activations, distort matching scores, and destabilize contrastive training under common training settings. To address this issue, we introduce a simple initialization-time correction that rescales the MLM-head projection by a constant factor before SPLADE training. This zero-cost adjustment improves training stability without modifying the model architecture or training objective. Across both in-domain and out-of-domain retrieval benchmarks, this simple correction substantially improves large-norm backbones such as ModernBERT and Ettin, turning unstable training runs into competitive sparse retrievers. In several settings, the corrected models further match or surpass the classic BERT-SPLADE baseline. These findings suggest that the bottleneck in adapting pretrained encoders to LSR is not encoder capacity alone, but the calibration of the MLM-head scale used to construct sparse lexical representations.

Youngjoon Jang, Seongtae Hong, Jonah Turner +1

Korea University Seoul, South Korea · Independent Seoul, South Korea

Masked Language Modeling Learned Sparse Retrieval Language Model Calibration Information Retrieval

Jun 2, 2026cs.CL

Knowledge Editing for Masked Diffusion Language Models

Knowledge editing aims to update or correct factual knowledge in a language model. A widely used approach, locate-then-edit, first localizes a fact within the model and then edits the weights there. To date, such methods have been developed exclusively for autoregressive models (ARMs). Whether they work for masked diffusion models (MDMs), which model text bidirectionally and generate by iterative denoising rather than next-token prediction, remains an open question. We address it by transferring locate-then-edit to MDMs and comparing multiple MDMs with their matched ARMs. Our central finding has two parts. First, where an edit should be applied transfers between them: the same early-to-mid-layer MLP at the last subject token is most effective for both. Second, this shared location does not guarantee a shared outcome. Single-token edits succeed in both, but as targets grow longer, editing degrades far more sharply in the MDMs than in the ARMs. The failure stems from how the edited fact is generated: producing a multi-token target passes through intermediate states in which the target is partially unmasked, for which the edit was never optimized. Guided by this diagnosis, we introduce a simple correction that optimizes the edit including such states, substantially restoring multi-token performance. Our code is available at https://github.com/holi-lab/MDM-KE.

Haewon Park, Yohan Jo

Graduate School of Data Science, Seoul National University

Knowledge Editing Masked Diffusion Models Masked Language Modeling Model Editing Diffusion Language Models Language Model Editing

May 27, 2026cs.AI

Entropy-aware Masking for Masked Language Modeling

Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context. This process enables the model to capture both syntactic and semantic properties of language. Conventionally, the tokens selected for masking are chosen at random, which may not always yield the most effective learning signals. In this work, we examine a token masking strategy based on entropy distribution. We use the model's entropy over token predictions to identify which tokens should be masked. This method aims to target tokens that are more informative and uncertain to improve the training efficacy. We also propose a novel self-masking approach that enhances training efficiency without relying on an external reference model. Experimental results demonstrate that our method achieves an average performance improvement of 5% in GLUE scores compared to the baseline. Further, we experiment with combining knowledge distillation with entropy masking, resulting in the best overall results.

Gokul Srinivasagan, Kai Hartung, Munir Georges

AImotion Bavaria, Technische Hochschule Ingolstadt, Germany

Masked Language Modeling Self-Supervised Pre-Training

May 20, 2026cs.LG

Towards Understanding Self-Pretraining for Sequence Classification

Amos et al. (2024) showed that the accuracy of Transformer models in sequence classification can be significantly improved by first pretraining with a masked token prediction objective without external data or augmentation, a procedure referred to as self-pretraining (SPT). While the primary objective of Amos et al. (2024) was to showcase that Transformers can achieve strong performance on the Long-Range Arena (LRA), their pipeline raises more fundamental questions: How does SPT drive optimization to better solutions? Why can standard supervised training fail in Transformers? To better understand this, we replicate and systematically ablate the findings of Amos et al. (2024). Our ablations suggest that a central bottleneck in the studied settings is not depth or generalization alone, but the ability of label supervision to learn useful query-key Attention patterns from random initialization. With a minimal setup, we identify learning proximity interactions - turning absolute positional encodings into proximity-biased Attention scores - as a key source of the improvements brought by SPT. Finally, in a simplified theoretical setup, we show that label supervision can be locally blind to certain Attention-score directions that are instead detectable through masked reconstruction.

Omar Coser, Loredana Zollo, Paolo Soda +1

Self-Attention Masked Language Modeling Self-Supervised Pre-Training Transformer Attention Positional Encoding Sequence Modeling

May 19, 2026cs.LG

Backdooring Masked Diffusion Language Models

Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive language models do not directly apply to MDLMs because MDLMs rely on discrete state corruption and iterative denoising rather than continuous noising or left-to-right prediction. In this work, we present the first systematic study of training-time backdoor attacks on MDLMs. We propose SHADOWMASK, a backdoor attack that modifies the MDLM forward corruption process by replacing the standard all-mask terminal distribution with a trigger-mask mixture prior. This creates a dedicated denoising pathway from trigger-corrupted states to attacker-specified targets while preserving clean denoising behavior. We further provide a principled mathematical formulation by defining the backdoored forward process, deriving the reverse-time posterior, and obtaining the continuous-time training objective. Evaluations on DiT-based MDLM and LLaDA-8B-Instruct across WikiText-103, OpenWebText, and Alpaca show that SHADOWMASK achieves near-100% attack success, substantially outperforms standard data poisoning, largely preserves clean utility, remains effective under full-model and parameter-efficient fine-tuning, and is robust against representative defenses.

Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou +3

Cornell University · Virginia Tech · IBM Research

LLM Backdoor Attacks Masked Diffusion Models Masked Language Modeling Diffusion Language Models

May 15, 2026cs.LG

Structure-Aware Masking for Protein Representation Learning

Masked language modeling (MLM) is the standard objective for training protein language models, typically implemented by randomly masking individual residues at a fixed rate (e.g., 15%). This practice implicitly assumes that all sequence positions contribute equally to representation learning. In downstream fitness prediction tasks, however, protein sequences are governed by three-dimensional structural dependencies and long-range residue contacts that induce strong nonlocal couplings between residues. We introduce Bucket Masking, a structure-aware masking strategy that selects groups of residues based on their proximity in three-dimensional space, preferentially masking structurally coupled regions during training. By conditioning the masking distribution on residue contacts, Bucket Masking shifts the learning objective toward modeling long-range interactions that are critical for protein function. Across four downstream protein fitness prediction tasks, Bucket Masking enables up to a 14% improvement over standard random masking, excelling at predicting higher-order mutational interactions. Through controlled ablations, we show that these improvements arise from mask placement rather than span size, establishing masking as a positional inductive bias.

Thomas Walton, Ayan Goel, Amirali Aghazadeh

Georgia Institute of Technology

Protein Fitness Prediction Masked Language Modeling Protein Language Models Molecular Property Prediction Protein Representation Learning

May 12, 2026cs.CL

A Causal Language Modeling Detour Improves Encoder Continued Pretraining

When adapting an encoder to a new domain, the standard approach is to continue training with Masked Language Modeling (MLM). We show that temporarily switching to Causal Language Modeling (CLM) followed by a short MLM decay improves downstream performance. On biomedical texts with ModernBERT, this CLM detour outperforms MLM baselines trained on identical data and compute across 8 French and 11 English biomedical tasks, by +1.2-2.8pp and +0.3-0.8pp respectively, depending on model size. We investigate the reasons for these gains. We find that CLM's dense supervision impacts low transformer layers (0-7) far more than MLM does. Freezing low layers during CLM eliminates the downstream benefit; freezing mid layers preserves it. The representational changes persist through the MLM decay phase, even when it matches the CLM phase in length, and they scale with model capacity. We release ModernCamemBERT-bio and ModernBERT-bio as state-of-the-art biomedical encoders in Base and Large sizes.

Rian Touchent, Eric de la Clergerie

Sorbonne Université / INRIA Paris · ALMAnaCH Team · INRIA Paris

Language Model Pretraining Masked Language Modeling Autoregressive Language Modeling Language Modeling Continued Pretraining

May 11, 2026cs.LG

Mixing Times of Glauber Dynamics on Masked Language Models

Masked language models (MLMs) define local conditional distributions over tokens but do not, in general, correspond to any consistent joint distribution over sequences. This raises a fundamental question: what global distributional behavior is induced when such conditionals are used iteratively for generation? We address this question by modeling iterative masked-token resampling as a Glauber dynamics Markov chain on the discrete space of token sequences. We first show that MLM conditionals are intrinsically incompatible: we introduce a rectangle test that certifies this incompatibility and empirically verify its prevalence across modern MLMs. We then provide a theoretical analysis of the induced Markov chain. Under bounded cross-token influence, we establish a high-temperature contraction result implying

O(n\log n)

mixing time where

n

is the sequence length. In contrast, we prove that under a uniform local margin condition, the chain exhibits metastability, with exponentially slow escape from semantic basins at low temperatures. Empirically, we demonstrate a phase transition in mixing behavior as a function of temperature and sequence length, consistent with the theoretical predictions. We further characterize the induced stationary behavior through semantic trajectories, identifying persistent structures such as long-lived traps and recurrent semantic basins, with political content serving as a measurable case study.

Suvadip Sana, Sami Wolf, Neer Mehta +4

Department of Statistics and Data Science Cornell University · Cornell University · Department Cornell of University Mathematics

Dynamical Systems Markov Chain Monte Carlo Masked Language Modeling Markov Models

May 8, 2026cs.LG

ProteinJEPA: Latent prediction improves protein language model pretraining

Protein language models are trained primarily with masked language modeling (MLM), which predicts masked amino-acid identities. Joint-embedding predictive architectures (JEPA) instead predict latent representations, but have not been applied to proteins. ProteinJEPA supplements MLM with a cosine loss for predicting the half-depth hidden states of a teacher given the unmasked sequence. On 19 tasks, with ESM2 at 35M and 150M parameters and three pretraining seeds, MLM+JEPA outperforms compute-matched and step-matched MLM-only continued training in 78 and 76 of 114 comparisons (14 losses, 22 ties). The median compute-matched gain is

+0.0106

on structure- and homology-sensitive tasks versus

+0.0041

elsewhere, led by SCOPe-40 retrieval and remote homology with improvements of 6.1 percentage points in Recall@1 and 2.7 points in accuracy, respectively. Gains on these tasks increase with model size from 8M to 150M. Against the off-the-shelf checkpoint, MLM+JEPA wins 81 of 114 comparisons (median

+0.0068

) without improving MLM loss. In random initialization the gain is smaller and replicates inconsistently across seeds (

p{=}0.059

). The same recipe improves the causal ProGen3 model, beating a compute-matched next-token-prediction control on 12 of 16 tasks. Ablations show that cosine loss beats mean squared error, while adding shallower targets removes most of the task gain. JEPA-only training collapses downstream performance: latent prediction complements MLM rather than replacing it. Code: https://anonymous.4open.science/r/protJepa-FF24

Dan Ofer, Dafna Shahaf, Michal Linial

Department of Biological Chemistry The Hebrew University of Jerusalem · School of Computer Science and Engineering The Hebrew University of Jerusalem

Language Model Pretraining Masked Language Modeling Joint-Embedding Predictive Architecture Protein Language Models Protein Representation Learning

May 2, 2026cs.IR

The Pre-Training Study of Expanded-SPLADE Models on Web Document Titles

Masked Language Modeling (MLM) pre-training is one of the primary ways to initialize Neural Information Retrieval (IR) models prior to retrieval fine-tuning. However, studies show that MLM pre-trained models have limited readiness and transfer learning issues for fine-tuning them into Neural Bi-Encoder models. This paper studies the effect of different pre-training datasets and pre-training options on the MLM pre-trained models for retrieval fine-tuning. The study focuses on the SPLADE-style model, which uses the MLM layer also at fine-tuning time. More specifically, we experimented with Expanded-SPLADE (ESPLADE) models, a specific instance of SPLADE models, and in-house web document titles are used as datasets. Pre-training, fine-tuning, and evaluation with optional test-time pruning of sparse vectors are conducted. Our observations are three-fold: First, fine-tuned models of higher retrieval effectiveness at both unpruned and most strict pruned settings are mostly pre-trained on a general corpus, and pre-trained with a higher learning rate, showing lower MLM accuracies. Second, in the most strict pruned setting, those models show higher-level retrieval cost and a higher variance in the length of the individual postings list. Third, the repetition of the general pre-training dataset does not have much effect on retrieval effectiveness. The experimentation empirically identifies the potential limitations for aligning MLM pre-training to ESPLADE fine-tuning. Also, the experimentation provides an empirical observation that, at most strict pruned settings, the retrieval effectiveness is better maintained by the higher-level retrieval cost, showing the trade-off relationship between the two in our setting.

Hiun Kim, Tae Kwan Lee, Taeryun Won

Naver Seongnam, South Korea

Language Model Pretraining Masked Language Modeling Information Retrieval

Apr 29, 2026cs.CL

A New Semisupervised Technique for Polarity Analysis using Masked Language Models

I developed a new version of Latent Semantic Scaling (LSS) employing word2vec as a masked language model. Unlike original spatial models, it assigns polarity scores to words and documents as predicted probabilities of seed words to occur in given contexts. These probabilistic polarity scores are more accurate, interpretable and consistent than those spatial polarity models can produce in text analysis. I demonstrate these advantages by applying both probabilistic and spatial models to China Daily's coverage of China and other countries during the coronavirus disease (COVID) pandemic in terms of achievement in health issues. The result suggests that more advanced masked language models would further improve the semisupervised machine learning technique.

Kohei Watanabe

Waseda University and LUT University

Masked Language Modeling Sentiment Analysis Semi-Supervised Learning

Apr 27, 2026cs.LG

On the Trainability of Masked Diffusion Language Models via Blockwise Locality

Masked diffusion language models (MDMs) have recently emerged as a promising alternative to standard autoregressive large language models (AR-LLMs), yet their optimization can be substantially less stable. We study blockwise MDMs and compare them with AR-LLMs on three controlled tasks that stress different aspects of structured generation: in-context linear regression, graph path-finding, and Sudoku solving. We find that standard random-masking MDMs fail to reliably learn linear regression, exhibit high variance training dynamics on graph path-finding, while outperforming AR-LLMs on Sudoku. To mitigate these instabilities, we propose two locality aware blockwise models, namely Jigsaw and Scatter, that inject left-to-right inductive bias by enforcing autoregressive locality within blocks while preserving iterative refinement at the block level. Empirically, Jigsaw matches AR-LLM stability on linear regression and remains strong on Sudoku, while Scatter retains diffusion's planning advantage on path-finding. Our results indicate that standard random-masking MDMs, even with blockwise variants, may be a suboptimal instantiation of diffusion LMs for ordered generation, motivating models beyond random masking.

Yuxiang Wang, Yu Xiang, Baojian Zhou +4

1Fudan University, Shanghai, China · 2Alibaba Group, China.

Masked Diffusion Models Masked Language Modeling Blockwise Diffusion Language Models Diffusion Language Models

Apr 17, 2026cs.LG

In Search of Lost DNA Sequence Pretraining

DNA sequence encoding is fundamental to gene function prediction, protein synthesis, and diverse downstream biological tasks. Despite the substantial progress achieved by large-scale DNA sequence pretraining, existing studies have overwhelmingly emphasized pretraining scale and custom downstream evaluation datasets, while neglecting some essential components of the pretraining paradigm. In this paper, we reveal three critical yet heretofore overlooked problems in DNA pretraining: inappropriate downstream datasets, inherent flaws in the neighbor-masking strategy, and the lack of detailed discussion on vocabulary. Therefore, we undertake comprehensive investigations and propose principled guidelines, including selection criteria for evaluation datasets, guiding task design, and in-depth vocabulary analysis. Extensive experiments validate the significance of our identified problems and support the rationale behind our recommendations. Finally, we introduce a standardized testbed that enables reproducible and rigorous benchmarking of DNA pretraining methods to advance the development of genomic foundation models.

Zhijiang Tang, Jiaxin Qi, Yan Cui +3

Computer Network Information Center, Chinese Academy of Sciences, Beijing, China · Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Zhejiang, China

Language Model Pretraining Masked Language Modeling Benchmark Design

Apr 16, 2026cs.CL

Predict and Reconstruct: Joint Objectives for Self-Supervised Language Representation Learning

Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are strongly anchored to surface-form token identity rather than deeper semantic structure. Inspired by the success of Joint Embedding Predictive Architectures (JEPA) (LeCun, 2022) in vision and audio, we propose a hybrid pre-training objective that combines a JEPA-style latent-space prediction loss with a standard MLM objective over a single shared encoder. A learnable scalar parameter continuously balances the two objectives during training. We pre-train both a hybrid model and a pure-MLM baseline on English Wikipedia using identical architectures and compute budgets (NVIDIA H100). Extensive representation analysis across five GLUE benchmarks (SST-2, MRPC, MNLI, CoLA, STS-B) using four pooling strategies reveals that the hybrid encoder produces significantly more uniform embeddings (uniformity less than -0.16 vs -0.05 for MLM), exhibits richer spectral geometry under max pooling, encodes less surface-level lexical information, and achieves a better semantic-to-lexical balance. Despite similar linear-probe downstream accuracy, the geometric differences are consistent and significant, suggesting that the JEPA predictive objective reshapes the latent space in ways that standard accuracy metrics alone cannot capture.

Aimen Boukhari

´Ecole Nationale Sup´erieure d’Informatique (ESI), Algiers , Algeria

Representation Geometry Masked Language Modeling Self-Supervised Learning Joint-Embedding Predictive Architecture Predictive Representation Learning Representation Geometry in Language Models

Nov 23, 2023cs.CL

General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level

The social biases and unwelcome stereotypes revealed by pretrained language models are becoming obstacles to their application. Compared to numerous debiasing methods targeting word level, there has been relatively less attention on biases present at phrase level, limiting the performance of debiasing in discipline domains. In this paper, we propose an automatic multi-token debiasing pipeline called \textbf{General Phrase Debiaser}, which is capable of mitigating phrase-level biases in masked language models. Specifically, our method consists of a \textit{phrase filter stage} that generates stereotypical phrases from Wikipedia pages as well as a \textit{model debias stage} that can debias models at the multi-token level to tackle bias challenges on phrases. The latter searches for prompts that trigger model's bias, and then uses them for debiasing. State-of-the-art results on standard datasets and metrics show that our approach can significantly reduce gender biases on both career and multiple disciplines, across models with varying parameter sizes.

Bingkang Shi, Xiaodan Zhang, Dehan Kong +4

Chinese Academy of Sciences, Institute of Information Engineering, Beijing 100093, China · Alibaba Group, Alibaba Artificial Intelligence Governance Laboratory, Beijing, China · University of Bristol, Department of Electrical and Electronic Engineering, Bristol, BS8 1UB, UK

Gender Bias in Language Models Debiased ML Masked Language Modeling Social Bias in Language Models Linguistic Bias in Language Models