Picture for Jonathan May

Jonathan May

What is a Good Question? Utility Estimation with LLM-based Simulations

Add code
Feb 24, 2025
Viaarxiv icon

Language Models Can Predict Their Own Behavior

Add code
Feb 18, 2025
Viaarxiv icon

Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL

Add code
Feb 18, 2025
Viaarxiv icon

Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning

Add code
Feb 13, 2025
Viaarxiv icon

NewsEdits 2.0: Learning the Intentions Behind Updating News

Add code
Nov 27, 2024
Figure 1 for NewsEdits 2.0: Learning the Intentions Behind Updating News
Figure 2 for NewsEdits 2.0: Learning the Intentions Behind Updating News
Figure 3 for NewsEdits 2.0: Learning the Intentions Behind Updating News
Figure 4 for NewsEdits 2.0: Learning the Intentions Behind Updating News
Viaarxiv icon

NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews

Add code
Nov 21, 2024
Figure 1 for NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews
Figure 2 for NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews
Figure 3 for NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews
Figure 4 for NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews
Viaarxiv icon

Personalized Help for Optimizing Low-Skilled Users' Strategy

Add code
Nov 14, 2024
Viaarxiv icon

Explaining Mixtures of Sources in News Articles

Add code
Nov 07, 2024
Viaarxiv icon

A Little Human Data Goes A Long Way

Add code
Oct 17, 2024
Figure 1 for A Little Human Data Goes A Long Way
Figure 2 for A Little Human Data Goes A Long Way
Figure 3 for A Little Human Data Goes A Long Way
Figure 4 for A Little Human Data Goes A Long Way
Viaarxiv icon

BotEval: Facilitating Interactive Human Evaluation

Add code
Jul 25, 2024
Viaarxiv icon