Picture for Jinhao Jiang

Jinhao Jiang

Technical Report: Enhancing LLM Reasoning with Reward-guided Tree Search

Add code
Nov 18, 2024
Viaarxiv icon

Towards Effective and Efficient Continual Pre-training of Large Language Models

Add code
Jul 26, 2024
Figure 1 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Figure 2 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Figure 3 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Figure 4 for Towards Effective and Efficient Continual Pre-training of Large Language Models
Viaarxiv icon

Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment

Add code
Jul 15, 2024
Viaarxiv icon

KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph

Add code
Feb 17, 2024
Viaarxiv icon

ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph

Add code
Dec 30, 2023
Viaarxiv icon

StructGPT: A General Framework for Large Language Model to Reason over Structured Data

Add code
May 16, 2023
Viaarxiv icon

A Survey of Large Language Models

Add code
Apr 27, 2023
Viaarxiv icon

UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph

Add code
Dec 02, 2022
Viaarxiv icon

Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models

Add code
May 04, 2022
Figure 1 for Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
Figure 2 for Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
Figure 3 for Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
Figure 4 for Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
Viaarxiv icon

Complex Knowledge Base Question Answering: A Survey

Add code
Aug 15, 2021
Figure 1 for Complex Knowledge Base Question Answering: A Survey
Figure 2 for Complex Knowledge Base Question Answering: A Survey
Figure 3 for Complex Knowledge Base Question Answering: A Survey
Figure 4 for Complex Knowledge Base Question Answering: A Survey
Viaarxiv icon