237 citations · 1.2k across the 87 of their papers we have counts for
7 papers · 1 filter
MEGen: Generative Backdoor into Large Language Models via Model Editing
Jiyang Qiu, Xinbei Ma, Zhuosheng Zhang +3
Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concern…
Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions
Xinbei Ma, Yiting Wang, Yao Yao +4
This paper investigates the faithfulness of multimodal large language model (MLLM) agents in a graphical user interface (GUI) environment, aiming to address the research question o…
DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems
Anni Zou, Wenhao Yu, Hongming Zhang +5
Recently, there has been a growing interest among large language model (LLM) developers in LLM-based document reading systems, which enable users to upload their own documents and…
Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering
Yexin Wu, Zhuosheng Zhang, Hai Zhao
Large language models have manifested remarkable capabilities by leveraging chain-of-thought (CoT) reasoning techniques to solve intricate questions through step-by-step reasoning…
CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation
Xinbei Ma, Zhuosheng Zhang, Hai Zhao
Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical…
On the Robustness of Editing Large Language Models
Xinbei Ma, Tianjie Ju, Jiyang Qiu +4
Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation…
GLaPE: Gold Label-agnostic Prompt Evaluation and Optimization for Large Language Model
Xuanchang Zhang, Zhuosheng Zhang, Hai Zhao
Despite the rapid progress of large language models (LLMs), their task performance remains sensitive to prompt design. Recent studies have explored leveraging the LLM itself as an…