activity
20242026
collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities

Ziwen Xu, Kewei Xu, Haoming Xu +8

Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…

cs.CL2026

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Haoming Xu, Ningyuan Zhao, Yunzhi Yao +7

As Large Language Models (LLMs) are increasingly deployed in real-world settings, correctness alone is insufficient. Reliable deployment requires maintaining truthful beliefs under…

cs.CL2025

LightMem: Lightweight and Efficient Memory-Augmented Generation

Jizhan Fang, Xinle Deng, Haoming Xu +9

Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory…

cs.CL2025

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

Haoming Xu, Shuxun Wang, Yanqiu Zhao +6

This paper presents the ZJUKLAB team's submission for SemEval-2025 Task 4: Unlearning Sensitive Content from Large Language Models. This task aims to selectively erase sensitive kn…

cs.CL2025

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

Ziwen Xu, Shuxun Wang, Kewei Xu +7

In this paper, we introduce EasyEdit2, a framework designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors. EasyEdit2 supports a wide ra…

cs.CL2025

ReLearn: Unlearning via Learning for Large Language Models

Haoming Xu, Ningyuan Zhao, Liming Yang +7

Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent token…