Summary of Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback, By Dong Won Lee et al.
Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedback
by Dong Won Lee, Hae Won Park, Yoon Kim, Cynthia Breazeal, Louis-Philippe Morency
First submitted to arxiv on: 17 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); 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 The proposed approach, dubbed GELI, aims to align a large language model (LLM)-based dialogue agent by leveraging global rewards and multimodal signals. The method decomposes the human-provided session-level reward into local, turn-level rewards using Local Implicit (LI) signals, which are then used to shape the reward decomposition step. This decomposed reward model is integrated into the RHLF pipeline to improve the LLM-based dialogue agent’s performance. Experimental results demonstrate consistent improvements across various conversational metrics compared to baseline methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary We explain a new way to make a computer chat with people better. The method uses two kinds of rewards: one for the whole conversation and one for each turn in the conversation. This helps the chatbot learn how to talk more naturally. We tested this approach and found it works better than other methods. |
Keywords
* Artificial intelligence * Large language model
