Picture for Xingxuan Li

Xingxuan Li

How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library

Add code
Mar 31, 2024
Figure 1 for How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library
Figure 2 for How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library
Figure 3 for How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library
Figure 4 for How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library
Viaarxiv icon

ParaICL: Towards Robust Parallel In-Context Learning

Mar 31, 2024
Viaarxiv icon

ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?

Add code
Dec 05, 2023
Viaarxiv icon

Unlocking Temporal Question Answering for Large Language Models Using Code Execution

Add code
May 24, 2023
Figure 1 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Figure 2 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Figure 3 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Figure 4 for Unlocking Temporal Question Answering for Large Language Models Using Code Execution
Viaarxiv icon

Is GPT-4 a Good Data Analyst?

Add code
May 24, 2023
Figure 1 for Is GPT-4 a Good Data Analyst?
Figure 2 for Is GPT-4 a Good Data Analyst?
Figure 3 for Is GPT-4 a Good Data Analyst?
Figure 4 for Is GPT-4 a Good Data Analyst?
Viaarxiv icon

Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases

Add code
May 22, 2023
Figure 1 for Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases
Figure 2 for Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases
Figure 3 for Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases
Figure 4 for Chain of Knowledge: A Framework for Grounding Large Language Models with Structured Knowledge Bases
Viaarxiv icon

Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework

Add code
May 05, 2023
Figure 1 for Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
Figure 2 for Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
Figure 3 for Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
Figure 4 for Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework
Viaarxiv icon

Retrieving Multimodal Information for Augmented Generation: A Survey

Mar 20, 2023
Figure 1 for Retrieving Multimodal Information for Augmented Generation: A Survey
Figure 2 for Retrieving Multimodal Information for Augmented Generation: A Survey
Viaarxiv icon

Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological Perspective

Add code
Dec 20, 2022
Figure 1 for Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological Perspective
Figure 2 for Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological Perspective
Figure 3 for Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological Perspective
Figure 4 for Is GPT-3 a Psychopath? Evaluating Large Language Models from a Psychological Perspective
Viaarxiv icon

Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations

Add code
Nov 16, 2022
Figure 1 for Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Figure 2 for Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Figure 3 for Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Figure 4 for Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Viaarxiv icon