7 papers
Adaptive Multi-Step Lookahead Decoding for Diffusion Language Models
Yingqian Cui, Wei Deng, Lantao Mei +4
Masked diffusion language models (DLMs) enable parallel text generation by iteratively refining masked tokens, offering a promising alternative to autoregressive decoding. Recent l…
"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems
Hang Li, Fedor Filippov, Yuping Lin +6
The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-foll…
Whole-Pool Setwise Reranking with Long-Context Language Models
Hang Li, Chuting Yu, Teerapong Leelanupab +2
Previous LLM-based passage re-rankers are often expensive and slow because the input context constraints require the LLM to make many dependent model calls. We study how recent lon…
Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs
Haoyu Han, Kai Guo, Harry Shomer +5
Reasoning over structured graphs remains a fundamental challenge for Large Language Models (LLMs), particularly when scaling to large graphs. Existing approaches typically follow t…
LLM-based Automated Grading with Human-in-the-Loop
Yucheng Chu, Hang Li, Kaiqi Yang +2
The rise of artificial intelligence (AI) technologies, particularly large language models (LLMs), has brought significant advancements to the field of education. Among various appl…
Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation
Yucheng Chu, Peng He, Hang Li +6
Short answer assessment is a vital component of science education, allowing evaluation of students' complex three-dimensional understanding. Large language models (LLMs) that posse…