Summary of Optimal Design For Human Preference Elicitation, by Subhojyoti Mukherjee et al.
Optimal Design for Human Preference Elicitation
by Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari, Aniket Deshmukh, Ge Liu, Yifei Ma, Branislav Kveton
First submitted to arxiv on: 22 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a novel approach to learning preference models from human feedback, focusing on efficient methods for eliciting preferences in scenarios where multiple answers are possible. By generalizing optimal designs, the authors develop policies that compute optimal information-gathering strategies for lists of items, which are then used to elicit preferences proportionally to their probability. The approach is demonstrated to be effective through experiments with absolute and ranking feedback models on existing question-answering problems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores ways to make it easier and cheaper to get people’s opinions about what they like or dislike. Instead of asking for one specific answer, the authors ask people to rank a list of options in order of preference. They then use this information to train machines to learn from these rankings. The approach is tested on real-world question-answering problems and shown to be practical. |
Keywords
» Artificial intelligence » Probability » Question answering
