activity
20242026
most citedMemory in the Age of AI Agents

1 citations · 1 across the 8 of their papers we have counts for

collaborators

9 papers

cs.CL2026

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Zhongxiang Sun, Yi Zhan, Chenglei Shen +4

Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We…

cs.CL20261 cited

Memory in the Age of AI Agents

Yuyang Hu, Shichun Liu, Yanwei Yue +44

Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attentio…

cs.CL2025

Balancing Stylization and Truth via Disentangled Representation Steering

Chenglei Shen, Zhongxiang Sun, Teng Shi +2

Generating stylized large language model (LLM) responses via representation editing is a promising way for fine-grained output control. However, there exists an inherent trade-off:…

cs.CL2025

An Explicit Syllogistic Legal Reasoning Framework for Large Language Models

Kepu Zhang, Weijie Yu, Zhongxiang Sun +1

Syllogistic reasoning is crucial for sound legal decision-making, allowing legal professionals to draw logical conclusions by applying general principles to specific case facts. Wh…

cs.AI2025

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective

Zhongxiang Sun, Qipeng Wang, Haoyu Wang +2

Large Reasoning Models (LRMs) have shown impressive capabilities in multi-step reasoning tasks. However, alongside these successes, a more deceptive form of model error has emerged…

cs.IR2025

QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors

Kepu Zhang, Zhongxiang Sun, Weijie Yu +5

Retriever-augmented generation (RAG) has become a widely adopted approach for enhancing the factual accuracy of large language models (LLMs). While current benchmarks evaluate the…