5 papers
A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization
Weixiao Zhou, Gengyao Li, Xianfu Cheng +3
Despite the significant advancement of LLMs in conversation summarization, their evaluation remains limited by insufficient scenarios, input lengths, and sample sizes. Furthermore,…
NeuroArmor: Safe-Variant-Guided Representation Consistency for Selective Re-Anchoring in Jailbreak Defense
Zhongyang Lin, Ziran Zhao, Feifei Zhai +1
Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translation, encoding, adversarial suffi…
What Are They Talking About? A Benchmark of Knowledge-Grounded Discussion Summarization
Weixiao Zhou, Junnan Zhu, Gengyao Li +4
Traditional dialogue summarization primarily focuses on dialogue content, assuming it comprises adequate information for a clear summary. However, this assumption often fails for d…
CROP: Contextual Region-Oriented Visual Token Pruning
Jiawei Guo, Feifei Zhai, Pu Jian +2
Current VLM-based VQA methods often process entire images, leading to excessive visual tokens that include redundant information irrelevant to the posed question. This abundance of…
TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification
Junnan Zhu, Min Xiao, Yining Wang +3
LLMs have achieved remarkable fluency and coherence in text generation, yet their widespread adoption has raised concerns about content reliability and accountability. In high-stak…