Picture for Cheng Qian

Cheng Qian

MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents

Add code
Mar 03, 2025
Viaarxiv icon

The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination

Add code
Feb 22, 2025
Figure 1 for The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
Figure 2 for The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
Figure 3 for The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
Figure 4 for The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination
Viaarxiv icon

SMART: Self-Aware Agent for Tool Overuse Mitigation

Add code
Feb 17, 2025
Figure 1 for SMART: Self-Aware Agent for Tool Overuse Mitigation
Figure 2 for SMART: Self-Aware Agent for Tool Overuse Mitigation
Figure 3 for SMART: Self-Aware Agent for Tool Overuse Mitigation
Figure 4 for SMART: Self-Aware Agent for Tool Overuse Mitigation
Viaarxiv icon

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Add code
Feb 13, 2025
Figure 1 for EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Figure 2 for EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Figure 3 for EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Figure 4 for EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Viaarxiv icon

Internal Activation as the Polar Star for Steering Unsafe LLM Behavior

Add code
Feb 04, 2025
Viaarxiv icon

EscapeBench: Pushing Language Models to Think Outside the Box

Add code
Dec 18, 2024
Viaarxiv icon

FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs

Add code
Oct 22, 2024
Viaarxiv icon

Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs

Add code
Oct 18, 2024
Figure 1 for Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
Figure 2 for Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
Figure 3 for Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
Figure 4 for Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
Viaarxiv icon

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Add code
Oct 16, 2024
Figure 1 for Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
Figure 2 for Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
Figure 3 for Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
Figure 4 for Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
Viaarxiv icon

Optimized Biomedical Question-Answering Services with LLM and Multi-BERT Integration

Add code
Oct 11, 2024
Viaarxiv icon