@inproceedings{kim-etal-2024-panda,
title = "{PANDA}: Persona Attributes Navigation for Detecting and Alleviating Overuse Problem in Large Language Models",
author = "Kim, Jinsung and
Koo, Seonmin and
Lim, Heuiseok",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.670",
pages = "12005--12026",
abstract = "In the persona-grounded dialogue (PGD) task, it is required not only to respond fluently, but also to ground the attributes according to the current conversation topic properly. However, due to their tendency to overly ground given attributes, LLMs often generate unnatural responses provoked by using attributes that deviate from the flow of the conversation or by exploiting too many attributes at once. We term this phenomenon the *overuse* problem of LLMs. Unfortunately, research devising precise criteria and frameworks to quantitatively verify LLMs{'} *overuse* problem is obviously insufficient. To address this issue, we propose **P**ersona **A**ttributes **N**avigation for **D**etecting and **A**lleviating the *overuse* problem (**PANDA**) framework. **PANDA** is the first study to quantify the persona *overuse* problem of LLMs by establishing clear standards of the problem and verifying various LLMs based on them. Moreover, this framework navigates us into understanding persona attributes by introducing diverse and detailed dialogue topics that consider practical conversation situations. We provide insights related to LLMs{'} persona attribute *overuse* problem through comprehensive verification and analysis with **PANDA** in the PGD task. Our code and resources can be found at http://github.com/jin62304/PANDA.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2024-panda">
<titleInfo>
<title>PANDA: Persona Attributes Navigation for Detecting and Alleviating Overuse Problem in Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinsung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seonmin</namePart>
<namePart type="family">Koo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heuiseok</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the persona-grounded dialogue (PGD) task, it is required not only to respond fluently, but also to ground the attributes according to the current conversation topic properly. However, due to their tendency to overly ground given attributes, LLMs often generate unnatural responses provoked by using attributes that deviate from the flow of the conversation or by exploiting too many attributes at once. We term this phenomenon the *overuse* problem of LLMs. Unfortunately, research devising precise criteria and frameworks to quantitatively verify LLMs’ *overuse* problem is obviously insufficient. To address this issue, we propose **P**ersona **A**ttributes **N**avigation for **D**etecting and **A**lleviating the *overuse* problem (**PANDA**) framework. **PANDA** is the first study to quantify the persona *overuse* problem of LLMs by establishing clear standards of the problem and verifying various LLMs based on them. Moreover, this framework navigates us into understanding persona attributes by introducing diverse and detailed dialogue topics that consider practical conversation situations. We provide insights related to LLMs’ persona attribute *overuse* problem through comprehensive verification and analysis with **PANDA** in the PGD task. Our code and resources can be found at http://github.com/jin62304/PANDA.</abstract>
<identifier type="citekey">kim-etal-2024-panda</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.670</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>12005</start>
<end>12026</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PANDA: Persona Attributes Navigation for Detecting and Alleviating Overuse Problem in Large Language Models
%A Kim, Jinsung
%A Koo, Seonmin
%A Lim, Heuiseok
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F kim-etal-2024-panda
%X In the persona-grounded dialogue (PGD) task, it is required not only to respond fluently, but also to ground the attributes according to the current conversation topic properly. However, due to their tendency to overly ground given attributes, LLMs often generate unnatural responses provoked by using attributes that deviate from the flow of the conversation or by exploiting too many attributes at once. We term this phenomenon the *overuse* problem of LLMs. Unfortunately, research devising precise criteria and frameworks to quantitatively verify LLMs’ *overuse* problem is obviously insufficient. To address this issue, we propose **P**ersona **A**ttributes **N**avigation for **D**etecting and **A**lleviating the *overuse* problem (**PANDA**) framework. **PANDA** is the first study to quantify the persona *overuse* problem of LLMs by establishing clear standards of the problem and verifying various LLMs based on them. Moreover, this framework navigates us into understanding persona attributes by introducing diverse and detailed dialogue topics that consider practical conversation situations. We provide insights related to LLMs’ persona attribute *overuse* problem through comprehensive verification and analysis with **PANDA** in the PGD task. Our code and resources can be found at http://github.com/jin62304/PANDA.
%U https://aclanthology.org/2024.emnlp-main.670
%P 12005-12026
Markdown (Informal)
[PANDA: Persona Attributes Navigation for Detecting and Alleviating Overuse Problem in Large Language Models](https://aclanthology.org/2024.emnlp-main.670) (Kim et al., EMNLP 2024)
ACL