Summary of Enhancing Ai Assisted Writing with One-shot Implicit Negative Feedback, by Benjamin Towle and Ke Zhou
Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback
by Benjamin Towle, Ke Zhou
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 This paper proposes Nifty, an approach that utilizes classifier guidance to incorporate implicit user feedback into text generation. It targets smart reply systems where users don’t select any suggested replies, using this as one-shot negative feedback to enhance AI writing models. The authors demonstrate up to 34% improvement in Rouge-L and 89% in generating correct intent compared to a vanilla AI system on MultiWOZ and Schema-Guided Dialog datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make computers better at communicating with people. They found a way to use feedback when someone doesn’t like the computer’s suggestions, which can improve how well it writes things. This could be useful for chatbots or other systems that need to understand what we mean. The new approach, called Nifty, is tested on two different datasets and shows some big improvements. |
Keywords
» Artificial intelligence » One shot » Rouge » Text generation
