5 papers
SpecAlign: Efficient Specification-Grounded Alignment of Large Language Models via Synthetic Data
Wenjie Wang, Yue Huang, Zhengqing Yuan +6
As large language models (LLMs) are increasingly deployed in real-world applications, alignment is no longer governed by a single universal notion of safety or helpfulness, but ins…
Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers
Yixuan Du, Chenxiao Yu, Haoyan Xu +3
Vision-Language Models (VLMs) integrate visual and textual knowledge into unified representations that increasingly underpin modern retrieval and recommendation systems. However, i…
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu +3
Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autor…
GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization
Ojas Nimase, Zhe Chen, Gengpei Qi +2
Large language models (LLMs) increasingly rank products, documents, and recommendations for user queries, which makes manipulating these rankings a growing concern for fairness and…
Fairness or Fluency? An Investigation into Language Bias of Pairwise LLM-as-a-Judge
Xiaolin Zhou, Zheng Luo, Yicheng Gao +4
Recent advances in Large Language Models (LLMs) have incentivized the development of LLM-as-a-judge, an application of LLMs where they are used as judges to decide the quality of a…