9 papers
RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation
Jiayang Yu, Jialun Zhong, Lei Zou
Retrieval-Augmented Generation (RAG) has become essential for knowledge-intensive question answering, yet scaling RAG pipelines remains challenging due to the prohibitive computati…
Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory
Sen Hu, Yuxiang Wei, Jiaxin Ran +5
Graph structures are increasingly used in dialog memory systems, but empirical findings on their effectiveness remain inconsistent, making it unclear which design choices truly mat…
Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
Jianpeng Hu, Yanzeng Li, Jialun Zhong +2
The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithful…
GAP: Graph-Assisted Prompts for Dialogue-based Medication Recommendation
Jialun Zhong, Yanzeng Li, Sen Hu +3
Medication recommendations have become an important task in the healthcare domain, especially in measuring the accuracy and safety of medical dialogue systems (MDS). Different from…
Exploiting Prefix-Tree in Structured Output Interfaces for Enhancing Jailbreak Attacking
Yanzeng Li, Yunfan Xiong, Jialun Zhong +3
The rise of Large Language Models (LLMs) has led to significant applications but also introduced serious security threats, particularly from jailbreak attacks that manipulate outpu…
DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure
Yunfan Xiong, Ruoyu Zhang, Yanzeng Li +2
While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly b…