collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

Understanding Sparse Attention Selectivity in Long-Context Foundation Models via Counterfactual Evaluation

Xingyu Ren, Youran Sun, Chugang Yi +1

Sparse attention is widely deployed in long-context serving stacks, yet no framework audits how discarding blocks changes the influence of specific content on model output. We firs…

cs.CL2026

Cross-Task Dissociation in Frontier Vision-Language Model Theory of Mind

Kejia Zhang, Youran Sun, Chugang Yi +1

Do frontier vision-language models present a coherent Theory-of-Mind (ToM) profile across tasks, matching the same human reference group, or does that profile fragment from one par…

cs.CL2026

PerspectiveGap: A Benchmark for Multi-Agent Orchestration Prompting

Youran Sun, Xingyu Ren, Kejia Zhang +2

Real-world LLM applications are moving beyond single-agent workflows toward orchestrated multi-agent systems, yet current models still struggle to determine what each sub-agent nee…

cs.CL2026

Correcting Mean Bias in Text Embeddings: A Refined Renormalization with Training-Free Improvements on MMTEB

Xingyu Ren, Youran Sun, Haoyu Liang

We find that current sentence-embedding models produce outputs with a consistent bias: every embedding decomposes as , where the mean is near-identical acro…

cs.CL2025

Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models

Haoyu Liang, Youran Sun, Yunfeng Cai +2

The security issue of large language models (LLMs) has gained wide attention recently, with various defense mechanisms developed to prevent harmful output, among which safeguards b…