LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915949795344384 |
|---|---|
| author | Kang, Haoqiang Zhang, Yizhe Kuang, Nikki Lijing Majamaki, Nicklas Jaitly, Navdeep Ma, Yi-An Qin, Lianhui |
| author_facet | Kang, Haoqiang Zhang, Yizhe Kuang, Nikki Lijing Majamaki, Nicklas Jaitly, Navdeep Ma, Yi-An Qin, Lianhui |
| contents | Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can also lead to inefficient exploration for diverse solutions. In this paper, we propose LaDiR} (Latent Diffusion Reasoner), a novel reasoning framework that unifies the expressiveness of continuous latent representation with the iterative refinement capabilities of latent diffusion models for an existing LLM. We first construct a structured latent reasoning space using a Variational Autoencoder (VAE) that encodes text reasoning steps into blocks of thought tokens, preserving semantic information and interpretability while offering compact but expressive representations. Subsequently, we utilize a latent diffusion model that learns to denoise a block of latent thought tokens with a blockwise bidirectional attention mask, enabling longer horizon and iterative refinement with adaptive test-time compute. This design, combined with explicit diversity guidance during diffusion inference, enables the generation of multiple diverse reasoning trajectories that explore distinct regions of the latent space, rather than producing repetitive solutions as often occurs in standard autoregressive sampling. We conduct evaluations on a suite of mathematical reasoning, code generation and puzzle planning benchmarks. Empirical results show that LaDiR consistently improves accuracy, diversity, and interpretability over existing autoregressive, diffusion-based, and latent reasoning methods, revealing a new paradigm for text reasoning with latent diffusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04573 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning Kang, Haoqiang Zhang, Yizhe Kuang, Nikki Lijing Majamaki, Nicklas Jaitly, Navdeep Ma, Yi-An Qin, Lianhui Machine Learning Artificial Intelligence Computation and Language Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can also lead to inefficient exploration for diverse solutions. In this paper, we propose LaDiR} (Latent Diffusion Reasoner), a novel reasoning framework that unifies the expressiveness of continuous latent representation with the iterative refinement capabilities of latent diffusion models for an existing LLM. We first construct a structured latent reasoning space using a Variational Autoencoder (VAE) that encodes text reasoning steps into blocks of thought tokens, preserving semantic information and interpretability while offering compact but expressive representations. Subsequently, we utilize a latent diffusion model that learns to denoise a block of latent thought tokens with a blockwise bidirectional attention mask, enabling longer horizon and iterative refinement with adaptive test-time compute. This design, combined with explicit diversity guidance during diffusion inference, enables the generation of multiple diverse reasoning trajectories that explore distinct regions of the latent space, rather than producing repetitive solutions as often occurs in standard autoregressive sampling. We conduct evaluations on a suite of mathematical reasoning, code generation and puzzle planning benchmarks. Empirical results show that LaDiR consistently improves accuracy, diversity, and interpretability over existing autoregressive, diffusion-based, and latent reasoning methods, revealing a new paradigm for text reasoning with latent diffusion. |
| title | LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2510.04573 |