@inproceedings{xia-etal-2024-measuring,
title = "Measuring Bargaining Abilities of {LLM}s: A Benchmark and A Buyer-Enhancement Method",
author = "Xia, Tian and
He, Zhiwei and
Ren, Tong and
Miao, Yibo and
Zhang, Zhuosheng and
Yang, Yang and
Wang, Rui",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.213",
doi = "10.18653/v1/2024.findings-acl.213",
pages = "3579--3602",
abstract = "Bargaining is an important and unique part of negotiation between humans. As LLM-driven agents learn to negotiate and act like real humans, how to evaluate agents{'} bargaining abilities remains an open problem.For the first time, we formally described the Bargaining task as an asymmetric incomplete information game, defining the gains of the Buyer and Seller in multiple bargaining processes. It allows us to quantitatively assess an agent{'}s performance in the Bargain task.We collected a real product price dataset, AmazonHistoryPrice, and conducted evaluations of various LLM agents{'} bargaining abilities. We find that playing a Buyer is much harder than a Seller, and increasing model size can not effectively improve the Buyer{'}s performance.To address the challenge, we propose a novel approach called OG-Narrator that integrates a deterministic Offer Generator to control the price range of Buyer{'}s offers, and an LLM Narrator to create natural language sentences for generated offers.Experimental results show that OG-Narrator improves the buyer{'}s deal rates from 26.67{\%} to 88.88{\%} and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xia-etal-2024-measuring">
<titleInfo>
<title>Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiwei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yibo</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuosheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Bargaining is an important and unique part of negotiation between humans. As LLM-driven agents learn to negotiate and act like real humans, how to evaluate agents’ bargaining abilities remains an open problem.For the first time, we formally described the Bargaining task as an asymmetric incomplete information game, defining the gains of the Buyer and Seller in multiple bargaining processes. It allows us to quantitatively assess an agent’s performance in the Bargain task.We collected a real product price dataset, AmazonHistoryPrice, and conducted evaluations of various LLM agents’ bargaining abilities. We find that playing a Buyer is much harder than a Seller, and increasing model size can not effectively improve the Buyer’s performance.To address the challenge, we propose a novel approach called OG-Narrator that integrates a deterministic Offer Generator to control the price range of Buyer’s offers, and an LLM Narrator to create natural language sentences for generated offers.Experimental results show that OG-Narrator improves the buyer’s deal rates from 26.67% to 88.88% and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned.</abstract>
<identifier type="citekey">xia-etal-2024-measuring</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.213</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.213</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>3579</start>
<end>3602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method
%A Xia, Tian
%A He, Zhiwei
%A Ren, Tong
%A Miao, Yibo
%A Zhang, Zhuosheng
%A Yang, Yang
%A Wang, Rui
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F xia-etal-2024-measuring
%X Bargaining is an important and unique part of negotiation between humans. As LLM-driven agents learn to negotiate and act like real humans, how to evaluate agents’ bargaining abilities remains an open problem.For the first time, we formally described the Bargaining task as an asymmetric incomplete information game, defining the gains of the Buyer and Seller in multiple bargaining processes. It allows us to quantitatively assess an agent’s performance in the Bargain task.We collected a real product price dataset, AmazonHistoryPrice, and conducted evaluations of various LLM agents’ bargaining abilities. We find that playing a Buyer is much harder than a Seller, and increasing model size can not effectively improve the Buyer’s performance.To address the challenge, we propose a novel approach called OG-Narrator that integrates a deterministic Offer Generator to control the price range of Buyer’s offers, and an LLM Narrator to create natural language sentences for generated offers.Experimental results show that OG-Narrator improves the buyer’s deal rates from 26.67% to 88.88% and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned.
%R 10.18653/v1/2024.findings-acl.213
%U https://aclanthology.org/2024.findings-acl.213
%U https://doi.org/10.18653/v1/2024.findings-acl.213
%P 3579-3602
Markdown (Informal)
[Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method](https://aclanthology.org/2024.findings-acl.213) (Xia et al., Findings 2024)
ACL