@inproceedings{hwang-etal-2023-aligning,
title = "Aligning Language Models to User Opinions",
author = "Hwang, EunJeong and
Majumder, Bodhisattwa and
Tandon, Niket",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.393",
doi = "10.18653/v1/2023.findings-emnlp.393",
pages = "5906--5919",
abstract = "An important aspect of developing LLMs that interact with humans is to align models{'} behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user group or ideological persona the model captured during its pertaining stage. But, how to best align an LLM with a specific user and not a demographic or ideological group remains an open question. Mining public opinion surveys (by PEW research), we find that the opinions of a user and their demographics and ideologies are not mutual predictors. We use this insight to align LLMs by modeling relevant past user opinions in addition to user demographics and ideology, achieving up to 7 points accuracy gains in predicting public opinions from survey questions across a broad set of topics. Our work opens up the research avenues to bring user opinions as an important ingredient in aligning language models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hwang-etal-2023-aligning">
<titleInfo>
<title>Aligning Language Models to User Opinions</title>
</titleInfo>
<name type="personal">
<namePart type="given">EunJeong</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bodhisattwa</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niket</namePart>
<namePart type="family">Tandon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An important aspect of developing LLMs that interact with humans is to align models’ behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user group or ideological persona the model captured during its pertaining stage. But, how to best align an LLM with a specific user and not a demographic or ideological group remains an open question. Mining public opinion surveys (by PEW research), we find that the opinions of a user and their demographics and ideologies are not mutual predictors. We use this insight to align LLMs by modeling relevant past user opinions in addition to user demographics and ideology, achieving up to 7 points accuracy gains in predicting public opinions from survey questions across a broad set of topics. Our work opens up the research avenues to bring user opinions as an important ingredient in aligning language models.</abstract>
<identifier type="citekey">hwang-etal-2023-aligning</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.393</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.393</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>5906</start>
<end>5919</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Language Models to User Opinions
%A Hwang, EunJeong
%A Majumder, Bodhisattwa
%A Tandon, Niket
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F hwang-etal-2023-aligning
%X An important aspect of developing LLMs that interact with humans is to align models’ behavior to their users. It is possible to prompt an LLM into behaving as a certain persona, especially a user group or ideological persona the model captured during its pertaining stage. But, how to best align an LLM with a specific user and not a demographic or ideological group remains an open question. Mining public opinion surveys (by PEW research), we find that the opinions of a user and their demographics and ideologies are not mutual predictors. We use this insight to align LLMs by modeling relevant past user opinions in addition to user demographics and ideology, achieving up to 7 points accuracy gains in predicting public opinions from survey questions across a broad set of topics. Our work opens up the research avenues to bring user opinions as an important ingredient in aligning language models.
%R 10.18653/v1/2023.findings-emnlp.393
%U https://aclanthology.org/2023.findings-emnlp.393
%U https://doi.org/10.18653/v1/2023.findings-emnlp.393
%P 5906-5919
Markdown (Informal)
[Aligning Language Models to User Opinions](https://aclanthology.org/2023.findings-emnlp.393) (Hwang et al., Findings 2023)
ACL
- EunJeong Hwang, Bodhisattwa Majumder, and Niket Tandon. 2023. Aligning Language Models to User Opinions. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5906–5919, Singapore. Association for Computational Linguistics.