Skip to content
#natural language processing Conference Open access

Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models

Sep 2026 · Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing · Vol abs/2609.28272 · 0 citations · 25 references
Computer Science

TL;DR

This work introduces a step-by-step token extraction procedure to extract causal shortcuts from data, and applies parallel prioritized masking on these tokens during training to enable efficient and accurate convergence to correct answers via causal shortcuts.

Abstract

Diffusion Language Models (DLMs) have attracted significant attention for their strong reasoning ability. However, under a bidirectional attention mechanism, DLMs operate over an exponentially large exploration space compared to autoregressive models (ARMs), making it challenging to focus on reasoning-guiding tokens under random masking. We define causal shortcuts as token chains that cover the full sequence and provide explicit guidance towards correct reasoning trajectories. We analyze the effects of causal shortcuts on the reasoning accuracy and convergence speed of DLMs, and find that they largely improve answer convergence efficiency and generation accuracy. Motivated by this, we propose a Causal Shortcut Learning (CSL) Framework for DLMs. Specifically, we introduce a step-by-step token extraction procedure to extract causal shortcuts from data, and apply parallel prioritized masking on these tokens during training to enable efficient and accurate convergence to correct answers via causal shortcuts. Extensive experiments across multiple reasoning benchmarks and two base models demonstrate that CSL consistently outperforms existing SFT-variant baselines, achieving an average improvement of $1.92\%$ over SFT-only models, and up to $4.20\%$ on MATH-500. The code is available at the \href{https://github.com/ZJUDianJin/Causal-Shortcuts-Learning}{https://github.com/ZJUDianJin/Causal-Shortcuts-Learning

Read PDF

Similar papers

#artificial intelligence Preprint Sep 2026

Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models

This work proposes stepwise risk-sensitive GRPO (StepRS-GRPO), which varies the risk coefficient of the group-advantage transformation across denoising states while retaining the underlying trainer, and shows that the diversity gains from StepRS-GRPO extend beyond final-answer strings.

Yue Yu, Bo-Wen Zuo, David J. Crandall et al. · 1 citation
#machine learning Preprint Sep 2026

CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models

CanvasAnneal is introduced, a curriculum-guided diffusion RL framework that improves over standard diffu-GRPO on MATH500, Countdown, and Tau2 and substantially accelerates reward improvement on several tasks, while gains are task-dependent.

Blake Olson, Yu-Hang Song, Emmett McQuinn et al. · 0 citations

Delayed Convergence and Emergent CoT Reliance in RL-Tuned Language Models

This analysis reveals that intermediate log-probability is an unreliable indicator for reasoning capability; instead, reasoning performance results from a shift of internal confidence allocation where RL fine-tuning delays internal convergence, exhibiting prolonged mid-layer exploration before converging sharply at the...

Pablo Pérez-Lázaro, Rocío Aznar-Gimeno, F. J. Lacueva-Pérez et al. · 0 citations
#natural language process... Preprint Sep 2026

Revisiting Complete Reasoning Traces for Post-Training

It is found that full trajectories provide only limited benefit, while partial trajectories are effective even under heavy truncation, and training LLMs using endpoints leads to consistent changes in reasoning behavior, and that it also benefits post-training methods based on reinforcement learning or on-policy distill...

Jaehui Hwang, Sangdoo Yun, Byeongho Heo et al. · 0 citations
Preprint Aug 2026

CAI-DLLM: Convergence Aware Inference for Diffusion Language Models

This work proposes CAI-DLLM, a training-free inference method that uses first-step confidence to guide denoising and reduce inference time, and evaluates CAI-DLLM on LLaDA-8B-Instruct and Dream-7B-Instruct across math, code, reasoning, commonsense, and long-context tasks.

Farhana Amin, Sabiha Afroz, D. Nikolopoulos · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.