3 citations · 3 across the 9 of their papers we have counts for
10 papers
How Causality Bridges the Semantic Gap
Shuhao Zhang, Xuran Zhou, Han Guo +2
Numerical measurements capture how a system behaves, but often leave the meanings of its variables unspecified. Some variables are measured but never labeled, and others are never…
LADDER: Graph-Guided Diffusion Language Models for Efficient Multi-Hop Reasoning
Senlei Zhang, Linhao Luo, Qian-Wen Zhang +4
Graph Retrieval-Augmented Generation (GraphRAG) has remarkably enhanced large language models on complex reasoning by leveraging structured entity topologies. However, existing fra…
Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices
Yaxin Li, Hao Wang, Yanda Shao +2
Vision-Language Models (VLMs) are rapidly deployed on human-facing wearable devices such as smart glasses to enable multimodal perception and AI-assisted decision-making. While pri…
Mental Damage: Caption Poisoning Attacks on Retrieval-Augmented Text-to-Music Generation
Yizhu Wen, Shuhao Zhang, Nan Zhang +2
Retrieval-augmented text-to-music (TTM) systems augment underspecified user prompts using captions retrieved from a music caption dataset. This design introduces an integrity depen…
LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
Qi Cao, Yufan Wang, Peijia Qin +2
Large language models (LLMs) often expose useful signals of self-monitoring: before solving a problem, they can estimate whether they are likely to succeed, and after solving it, t…
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
Luan Zhang, Dandan Song, Zhijing Wu +8
Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code interpreters (CI). Most recent s…
Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense
Shuhao Zhang, Jiarui Li, Qi Cao +2
Prompt-injection detectors are heterogeneous: each is strong on a different slice of attacks, and none is always reliable. Yet existing systems still treat detection as a fixed sin…
ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
Huipeng Ma, Luan Zhang, Dandan Song +10
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inher…
Ferret: An Efficient Online Continual Learning Framework under Varying Memory Constraints
Yuhao Zhou, Yuxin Tian, Jindi Lv +5
In the realm of high-frequency data streams, achieving real-time learning within varying memory constraints is paramount. This paper presents Ferret, a comprehensive framework desi…
A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis
Changzhi Zhou, Dandan Song, Yuhang Tian +6
Recently, Large Language Models (LLMs) have garnered increasing attention in the field of natural language processing, revolutionizing numerous downstream tasks with powerful reaso…