@inproceedings{liu-etal-2022-aligning,
title = "Aligning Generative Language Models with Human Values",
author = "Liu, Ruibo and
Zhang, Ge and
Feng, Xinyu and
Vosoughi, Soroush",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.18",
doi = "10.18653/v1/2022.findings-naacl.18",
pages = "241--252",
abstract = "Although current large-scale generative language models (LMs) can show impressive insights about factual knowledge, they do not exhibit similar success with respect to human values judgements (e.g., whether or not the generations of an LM are moral). Existing methods learn human values either by directly mimicking the behavior of human data, or rigidly constraining the generation space to human-chosen tokens. These methods are inherently limited in that they do not consider the contextual and abstract nature of human values and as a result often fail when dealing with out-of-domain context or sophisticated and abstract human values. This paper proposes SENSEI, a new reinforcement learning based method that can embed human values judgements into each step of language generation. SENSEI deploys an Actor-Critic framework, where the Critic is a reward distributor that simulates the reward assignment procedure of humans, while the Actor guides the generation towards the maximum reward direction. Compared with five existing methods in three human values alignment datasets, SENSEI not only achieves higher alignment performance in terms of both automatic and human evaluations, but also shows improvements on robustness and transfer learning on unseen human values.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2022-aligning">
<titleInfo>
<title>Aligning Generative Language Models with Human Values</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruibo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soroush</namePart>
<namePart type="family">Vosoughi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although current large-scale generative language models (LMs) can show impressive insights about factual knowledge, they do not exhibit similar success with respect to human values judgements (e.g., whether or not the generations of an LM are moral). Existing methods learn human values either by directly mimicking the behavior of human data, or rigidly constraining the generation space to human-chosen tokens. These methods are inherently limited in that they do not consider the contextual and abstract nature of human values and as a result often fail when dealing with out-of-domain context or sophisticated and abstract human values. This paper proposes SENSEI, a new reinforcement learning based method that can embed human values judgements into each step of language generation. SENSEI deploys an Actor-Critic framework, where the Critic is a reward distributor that simulates the reward assignment procedure of humans, while the Actor guides the generation towards the maximum reward direction. Compared with five existing methods in three human values alignment datasets, SENSEI not only achieves higher alignment performance in terms of both automatic and human evaluations, but also shows improvements on robustness and transfer learning on unseen human values.</abstract>
<identifier type="citekey">liu-etal-2022-aligning</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.18</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.18</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>241</start>
<end>252</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Generative Language Models with Human Values
%A Liu, Ruibo
%A Zhang, Ge
%A Feng, Xinyu
%A Vosoughi, Soroush
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F liu-etal-2022-aligning
%X Although current large-scale generative language models (LMs) can show impressive insights about factual knowledge, they do not exhibit similar success with respect to human values judgements (e.g., whether or not the generations of an LM are moral). Existing methods learn human values either by directly mimicking the behavior of human data, or rigidly constraining the generation space to human-chosen tokens. These methods are inherently limited in that they do not consider the contextual and abstract nature of human values and as a result often fail when dealing with out-of-domain context or sophisticated and abstract human values. This paper proposes SENSEI, a new reinforcement learning based method that can embed human values judgements into each step of language generation. SENSEI deploys an Actor-Critic framework, where the Critic is a reward distributor that simulates the reward assignment procedure of humans, while the Actor guides the generation towards the maximum reward direction. Compared with five existing methods in three human values alignment datasets, SENSEI not only achieves higher alignment performance in terms of both automatic and human evaluations, but also shows improvements on robustness and transfer learning on unseen human values.
%R 10.18653/v1/2022.findings-naacl.18
%U https://aclanthology.org/2022.findings-naacl.18
%U https://doi.org/10.18653/v1/2022.findings-naacl.18
%P 241-252
Markdown (Informal)
[Aligning Generative Language Models with Human Values](https://aclanthology.org/2022.findings-naacl.18) (Liu et al., Findings 2022)
ACL
- Ruibo Liu, Ge Zhang, Xinyu Feng, and Soroush Vosoughi. 2022. Aligning Generative Language Models with Human Values. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 241–252, Seattle, United States. Association for Computational Linguistics.