Picture for Xiaolong Jin

Xiaolong Jin

An Investigation on Group Query Hallucination Attacks

Add code
Aug 26, 2025
Viaarxiv icon

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

Add code
Aug 05, 2025
Viaarxiv icon

A Survey of Link Prediction in N-ary Knowledge Graphs

Add code
Jun 10, 2025
Viaarxiv icon

KnowCoder-V2: Deep Knowledge Analysis

Add code
Jun 07, 2025
Viaarxiv icon

Mixture Policy based Multi-Hop Reasoning over N-tuple Temporal Knowledge Graphs

Add code
May 19, 2025
Viaarxiv icon

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills

Add code
Apr 09, 2025
Figure 1 for SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Figure 2 for SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Figure 3 for SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Figure 4 for SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Viaarxiv icon

Towards Robust Universal Information Extraction: Benchmark, Evaluation, and Solution

Add code
Mar 05, 2025
Viaarxiv icon

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction

Add code
Mar 04, 2025
Viaarxiv icon

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs

Add code
Feb 28, 2025
Viaarxiv icon

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Add code
Feb 20, 2025
Viaarxiv icon