Picture for Joseph Chee Chang

Joseph Chee Chang

Penalizing Transparency? How AI Disclosure and Author Demographics Shape Human and AI Judgments About Writing

Add code
Jul 02, 2025
Viaarxiv icon

SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks

Add code
Jul 01, 2025
Viaarxiv icon

Ai2 Scholar QA: Organized Literature Synthesis with Attribution

Add code
Apr 15, 2025
Viaarxiv icon

Cocoa: Co-Planning and Co-Execution with AI Agents

Add code
Dec 14, 2024
Figure 1 for Cocoa: Co-Planning and Co-Execution with AI Agents
Figure 2 for Cocoa: Co-Planning and Co-Execution with AI Agents
Figure 3 for Cocoa: Co-Planning and Co-Execution with AI Agents
Figure 4 for Cocoa: Co-Planning and Co-Execution with AI Agents
Viaarxiv icon

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

Add code
Nov 21, 2024
Figure 1 for OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
Figure 2 for OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
Figure 3 for OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
Figure 4 for OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
Viaarxiv icon

Contextualized Evaluations: Taking the Guesswork Out of Language Model Evaluations

Add code
Nov 11, 2024
Figure 1 for Contextualized Evaluations: Taking the Guesswork Out of Language Model Evaluations
Figure 2 for Contextualized Evaluations: Taking the Guesswork Out of Language Model Evaluations
Figure 3 for Contextualized Evaluations: Taking the Guesswork Out of Language Model Evaluations
Figure 4 for Contextualized Evaluations: Taking the Guesswork Out of Language Model Evaluations
Viaarxiv icon

LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions

Add code
Oct 30, 2024
Figure 1 for LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions
Figure 2 for LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions
Figure 3 for LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions
Figure 4 for LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptions
Viaarxiv icon

ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models

Add code
Oct 25, 2024
Figure 1 for ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models
Figure 2 for ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models
Figure 3 for ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models
Figure 4 for ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models
Viaarxiv icon

IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback

Add code
Oct 05, 2024
Figure 1 for IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
Figure 2 for IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
Figure 3 for IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
Figure 4 for IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
Viaarxiv icon

A Design Space for Intelligent and Interactive Writing Assistants

Add code
Mar 26, 2024
Figure 1 for A Design Space for Intelligent and Interactive Writing Assistants
Figure 2 for A Design Space for Intelligent and Interactive Writing Assistants
Figure 3 for A Design Space for Intelligent and Interactive Writing Assistants
Figure 4 for A Design Space for Intelligent and Interactive Writing Assistants
Viaarxiv icon