Summary of Assistive Large Language Model Agents For Socially-aware Negotiation Dialogues, by Yuncheng Hua et al.
Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues
by Yuncheng Hua, Lizhen Qu, Gholamreza Haffari
First submitted to arxiv on: 29 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 develops assistive agents based on Large Language Models (LLMs) to aid in business negotiations. It simulates negotiations by letting two LLM-based agents engage in role play, with a third LLM acting as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes. The authors introduce an In-Context Learning (ICL) method that identifies high-quality exemplars without requiring labels or tuning. This approach is applied to three different negotiation topics and demonstrates effectiveness through empirical evidence. The paper’s contributions include the novel value impact criteria for measuring negotiation outcome quality and the release of its source code and generated dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps people negotiate better in business by creating special computer programs that can talk like humans. These programs, called Large Language Models (LLMs), are trained to have conversations just like we do. The LLMs are given tasks to help them learn how to be good negotiators. One of the main ideas is a “remediator” agent that helps fix problems in the conversation when someone says something that’s not nice or fair. This makes the negotiation go better and more people can agree on things. The paper shows that this approach works well for different types of negotiations. |
