activity
20232026
most citedMLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

3 citations · 4 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2025

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

Kangwei Liu, Siyuan Cheng, Bozhong Tian +7

Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the ov…

cs.CL2025

ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems

Chenxi Wang, Jizhan Fang, Xiang Chen +4

Recent advancements in Large Multimodal Models (LMMs) have shown promise in Autonomous Driving Systems (ADS). However, their direct application to ADS is hindered by challenges suc…

cs.CL20243 cited

MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Chenxi Wang, Xiang Chen, Ningyu Zhang +4

Multimodal Large Language Models (MLLMs) frequently exhibit hallucination phenomena, but the underlying reasons remain poorly understood. In this paper, we present an empirical ana…

cs.CL2024

To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng +6

Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in kn…

cs.CL2024

MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing

Jiaqi Li, Miaozeng Du, Chuanyi Zhang +6

Multimodal knowledge editing represents a critical advancement in enhancing the capabilities of Multimodal Large Language Models (MLLMs). Despite its potential, current benchmarks…

cs.CL2024

InstructEdit: Instruction-based Knowledge Editing for Large Language Models

Ningyu Zhang, Bozhong Tian, Siyuan Cheng +6

Knowledge editing for large language models can offer an efficient solution to alter a model's behavior without negatively impacting the overall performance. However, the current a…