3 papers
cs.CL2026
Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models
Miao Li, Hanyang Jiang, Sikai Cheng +6
Diffusion Language Models (DLMs) present a promising non-sequential paradigm for text generation, distinct from standard autoregressive (AR) approaches. However, current decoding s…
cs.LG2026
Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
Miaomiao Li, Hao Chen, Yang Wang +5
Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs inherently reflect biases in their trai…
cs.AI2026
SciTrek: Evaluating and Improving Long-Context Numerical Reasoning over Scientific Articles
Miao Li, Alexander Gurung, Irina Saparina +1
We introduce SciTrek, a synthetic question-answering dataset for assessing and improving long-context numerical reasoning in large language models (LLMs). Existing long-context dat…