6 papers
Beyond Query Similarity: Safety-Conditioned Cache Routing for LLM Response Reuse
Shilong Pan, Zhiliang Tian, Weiguo Chen +2
Semantic response caching reuses a cached response for a semantically similar query to improve LLM inference efficiency. However, query similarity alone can lead to unsafe reuse wh…
Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent Workflows
Shilong Pan, Zhiliang Tian, Zihan Chen +3
LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Exist…
DPRM: A Dual Implicit Process Reward Model in Multi-Hop Question Answering
Xinyi Wang, Yiping Song, Zhiliang Tian +3
In multi-hop question answering (MHQA) tasks, Chain of Thought (CoT) improves the quality of generation by guiding large language models (LLMs) through multi-step reasoning, and Kn…
RLJP: Legal Judgment Prediction via First-Order Logic Rule-enhanced with Large Language Models
Yue Zhang, Zhiliang Tian, Shicheng Zhou +7
Legal Judgment Prediction (LJP) is a pivotal task in legal AI. Existing semantic-enhanced LJP models integrate judicial precedents and legal knowledge for high performance. But the…
Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
Zhihua Wen, Zhiliang Tian, Zexin Jian +5
Large Language Models (LLMs) are widely used for knowledge-seeking yet suffer from hallucinations. The knowledge boundary (KB) of an LLM limits its factual understanding, beyond wh…
360REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System
Shen Gao, Hao Li, Chengrui Huang +4
Large language model agents have demonstrated remarkable advancements across various complex tasks. Recent works focus on optimizing the agent team or employing self-reflection to…