Picture for Yangyi Chen

Yangyi Chen

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales

Add code
May 31, 2024
Viaarxiv icon

Executable Code Actions Elicit Better LLM Agents

Add code
Feb 01, 2024
Viaarxiv icon

ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation

Add code
Nov 22, 2023
Figure 1 for ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
Figure 2 for ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
Figure 3 for ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
Figure 4 for ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation
Viaarxiv icon

DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback

Add code
Nov 16, 2023
Figure 1 for DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
Figure 2 for DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
Figure 3 for DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
Figure 4 for DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback
Viaarxiv icon

R-Tuning: Teaching Large Language Models to Refuse Unknown Questions

Add code
Nov 16, 2023
Figure 1 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Figure 2 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Figure 3 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Figure 4 for R-Tuning: Teaching Large Language Models to Refuse Unknown Questions
Viaarxiv icon

Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown

Add code
Nov 16, 2023
Figure 1 for Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown
Figure 2 for Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown
Figure 3 for Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown
Figure 4 for Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown
Viaarxiv icon

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

Add code
Sep 29, 2023
Figure 1 for CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Figure 2 for CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Figure 3 for CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Figure 4 for CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Viaarxiv icon

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

Add code
Sep 19, 2023
Figure 1 for MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Figure 2 for MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Figure 3 for MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Figure 4 for MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Viaarxiv icon

Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models

Add code
Sep 08, 2023
Figure 1 for Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
Figure 2 for Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
Figure 3 for Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
Figure 4 for Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models
Viaarxiv icon

Making Pre-trained Language Models both Task-solvers and Self-calibrators

Add code
Jul 21, 2023
Viaarxiv icon