Picture for Zhibin Gou

Zhibin Gou

Rho-1: Not All Tokens Are What You Need

Add code
Apr 11, 2024
Viaarxiv icon

Exploring the Mystery of Influential Data for Mathematical Reasoning

Add code
Apr 01, 2024
Viaarxiv icon

CriticBench: Benchmarking LLMs for Critique-Correct Reasoning

Add code
Mar 08, 2024
Viaarxiv icon

Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning

Add code
Mar 04, 2024
Figure 1 for Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning
Figure 2 for Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning
Figure 3 for Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning
Figure 4 for Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning
Viaarxiv icon

SciAgent: Tool-augmented Language Models for Scientific Reasoning

Add code
Feb 21, 2024
Viaarxiv icon

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

Add code
Oct 04, 2023
Figure 1 for ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Figure 2 for ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Figure 3 for ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Figure 4 for ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Viaarxiv icon

MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction

Add code
May 22, 2023
Figure 1 for MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction
Figure 2 for MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction
Figure 3 for MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction
Figure 4 for MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction
Viaarxiv icon

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

Add code
May 19, 2023
Figure 1 for CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Figure 2 for CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Figure 3 for CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Figure 4 for CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Viaarxiv icon

Long Time No See! Open-Domain Conversation with Long-Term Persona Memory

Add code
Mar 14, 2022
Figure 1 for Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Figure 2 for Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Figure 3 for Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Figure 4 for Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Viaarxiv icon