Image de couverture de livre

ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ye, Junjie, Li, Sixian, Li, Guanyu, Huang, Caishuang, Gao, Songyang, Wu, Yilong, Zhang, Qi, Gui, Tao, Huang, Xuanjing
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning
par: Ye, Junjie, et autres
Publié: (2024)

ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
par: Ye, Junjie, et autres
Publié: (2024)

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
par: Ye, Junjie, et autres
Publié: (2024)

FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
par: Huang, Caishuang, et autres
Publié: (2026)

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
par: Lv, Huijie, et autres
Publié: (2024)

CCTU: A Benchmark for Tool Use under Complex Constraints
par: Ye, Junjie, et autres
Publié: (2026)

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
par: Huang, Caishuang, et autres
Publié: (2024)

Unveiling Linguistic Regions in Large Language Models
par: Zhang, Zhihao, et autres
Publié: (2024)

Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
par: Ye, Junjie, et autres
Publié: (2025)

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
par: Ye, Junjie, et autres
Publié: (2025)

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models
par: Ye, Junjie, et autres
Publié: (2025)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
par: Xi, Zhiheng, et autres
Publié: (2023)

LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition
par: Ye, Junjie, et autres
Publié: (2024)

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
par: Zhang, Ming, et autres
Publié: (2024)

Navigating the OverKill in Large Language Models
par: Shi, Chenyu, et autres
Publié: (2024)

Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data
par: Xia, Han, et autres
Publié: (2024)

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition
par: Yang, Yuming, et autres
Publié: (2024)

VLSBench: Unveiling Visual Leakage in Multimodal Safety
par: Hu, Xuhao, et autres
Publié: (2024)

EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
par: Zhou, Weikang, et autres
Publié: (2024)

Are Large Language Models Good Prompt Optimizers?
par: Ma, Ruotian, et autres
Publié: (2024)

LLaMA Beyond English: An Empirical Study on Language Capability Transfer
par: Zhao, Jun, et autres
Publié: (2024)

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
par: Zhu, Dingwei, et autres
Publié: (2026)

CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios
par: Huang, Shiting, et autres
Publié: (2025)

RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions
par: Zhang, Yuansen, et autres
Publié: (2024)

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
par: Hu, Xuhao, et autres
Publié: (2026)

60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering
par: Ye, Junjie, et autres
Publié: (2024)

Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
par: Xi, Zhiheng, et autres
Publié: (2025)

FamilyTool: A Multi-hop Personalized Tool Use Benchmark
par: Wang, Yuxin, et autres
Publié: (2025)

Self-Consistency of the Internal Reward Models Improves Self-Rewarding Language Models
par: Zhou, Xin, et autres
Publié: (2025)

Unveiling the Truth and Facilitating Change: Towards Agent-based Large-scale Social Movement Simulation
par: Mou, Xinyi, et autres
Publié: (2024)

MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning
par: Wang, Chenyu, et autres
Publié: (2024)

Safe Inputs but Unsafe Output: Benchmarking Cross-modality Safety Alignment of Large Vision-Language Model
par: Wang, Siyin, et autres
Publié: (2024)

AutoTool: Efficient Tool Selection for Large Language Model Agents
par: Jia, Jingyi, et autres
Publié: (2025)

Secrets of RLHF in Large Language Models Part II: Reward Modeling
par: Wang, Binghai, et autres
Publié: (2024)

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels
par: Ye, Junjie, et autres
Publié: (2025)

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
par: He, Wei, et autres
Publié: (2024)

Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
par: Xu, Ningyu, et autres
Publié: (2026)

MatTools: Benchmarking Large Language Models for Materials Science Tools
par: Liu, Siyu, et autres
Publié: (2025)

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
par: Ding, Hanxing, et autres
Publié: (2025)

GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
par: Wang, Jize, et autres
Publié: (2026)