7 papers
Query-Adaptive Neuron Steering for LLMs
Yanxi Pan, Jingwen Wu, Yan Ma +8
Effectively eliciting the capabilities of large language models (LLMs) at inference time remains an important challenge. Existing studies address this challenge through context eng…
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models
Xinyi Zeng, Xue Yang, Jingyuan Zhang +5
Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak…
DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models
Lifan Zheng, Xue Yang, Jiawei Chen +6
With the widespread adoption of large language models (LLMs), understanding their personality representation mechanisms has become critical. As a novel paradigm in Personality Edit…
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models
Shaokai He, Kaiwen Wei, Xinyi Zeng +5
The "reversal curse" refers to the phenomenon where large language models (LLMs) exhibit predominantly unidirectional behavior when processing logically bidirectional relationships…
MobileRAG: Enhancing Mobile Agent with Retrieval-Augmented Generation
Gowen Loo, Chang Liu, Qinghong Yin +4
Smartphones have become indispensable in people's daily lives, permeating nearly every aspect of modern society. With the continuous advancement of large language models (LLMs), nu…
Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum
Xinglong Yang, Quan Feng, Zhongying Pan +7
The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both mod…
Enhancing Knowledge Density via Hierarchical Context Pruning for Retrieval-Augmented Repository-Level Code Completion
Xiaohan Chen, Zhongying Pan, Quan Feng +9
Retrieval-Augmented Generation (RAG) has advanced repository-level code completion by retrieving external code snippets, API documentation, or type definitions to expand the model'…