Research map / Large language models / Language, safety and interpretability
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta, Yilong Qin, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Andrej Risteski
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
The paper proposes a theoretical framework for generative masked language models (MLMs) and derives practical guidelines, but the provided text is only the ICML 2024 formatting template rather than the paper's content.
Problem
Limited mathematical understanding of the fundamental power and limitations of generative masked language models compared with autoregressive LMs, per the abstract.
Approach
Provides a theoretical framework for generative masked language modeling (per the abstract) with practical guidelines; the supplied body text is an ICML template and does not show the method.
Limitations
- Supplied full text is the ICML formatting template, so the paper's results could not be verified
Closest papers by meaning
- Scaling up Masked Diffusion Models on Text (ICLR 2025 · similarity 0.91)
- Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling (ICLR 2025 · similarity 0.90)
- Theoretical Benefit and Limitation of Diffusion Language Model (NeurIPS 2025 · similarity 0.90)
- Reflection-Window Decoding: Text Generation with Selective Refinement (ICML 2025 · similarity 0.90)
- Simple and Effective Masked Diffusion Language Models (NeurIPS 2024 · similarity 0.89)
- Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
