@inproceedings{reddy-liu-2026-geometric,
title = "A Geometric Perspective on Stabilizing Value Conflict Resolution",
author = "Reddy, Saket and
Liu, Andy",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.260/",
pages = "5761--5785",
ISBN = "979-8-89176-439-2",
abstract = "Large Language Models (LLMs) often struggle to navigate user requests that contain complex value conflicts, as direct scalar rewards are often ill-equipped to handle these scenarios. To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain. Geometrically, we show that CoT correlates with further smoothing the model{'}s loss landscape in its sharpest direction, helping resolve the optimization instability of traditional scalar rewards. In terms of performance, we demonstrate via relevant downstream benchmarks that CoT may increase capability, demonstrating that value conflict-focused CoT has the potential to be an effective mechanism for better moral reasoning. To capitalize on this potential, we create a new value conflict-focused CoT design that correlates with further smoothing the sharpest direction of the loss landscape and further increases moral reasoning performance. This finding shows that explicitly modifying and improving the design of reasoning dynamics offers a promising avenue for advancing pluralistic alignment in LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reddy-liu-2026-geometric">
<titleInfo>
<title>A Geometric Perspective on Stabilizing Value Conflict Resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saket</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) often struggle to navigate user requests that contain complex value conflicts, as direct scalar rewards are often ill-equipped to handle these scenarios. To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain. Geometrically, we show that CoT correlates with further smoothing the model’s loss landscape in its sharpest direction, helping resolve the optimization instability of traditional scalar rewards. In terms of performance, we demonstrate via relevant downstream benchmarks that CoT may increase capability, demonstrating that value conflict-focused CoT has the potential to be an effective mechanism for better moral reasoning. To capitalize on this potential, we create a new value conflict-focused CoT design that correlates with further smoothing the sharpest direction of the loss landscape and further increases moral reasoning performance. This finding shows that explicitly modifying and improving the design of reasoning dynamics offers a promising avenue for advancing pluralistic alignment in LLMs.</abstract>
<identifier type="citekey">reddy-liu-2026-geometric</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.260/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>5761</start>
<end>5785</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Geometric Perspective on Stabilizing Value Conflict Resolution
%A Reddy, Saket
%A Liu, Andy
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F reddy-liu-2026-geometric
%X Large Language Models (LLMs) often struggle to navigate user requests that contain complex value conflicts, as direct scalar rewards are often ill-equipped to handle these scenarios. To address this challenge, we investigate how chain-of-thought (CoT) reasoning can help improve performance in this domain. Geometrically, we show that CoT correlates with further smoothing the model’s loss landscape in its sharpest direction, helping resolve the optimization instability of traditional scalar rewards. In terms of performance, we demonstrate via relevant downstream benchmarks that CoT may increase capability, demonstrating that value conflict-focused CoT has the potential to be an effective mechanism for better moral reasoning. To capitalize on this potential, we create a new value conflict-focused CoT design that correlates with further smoothing the sharpest direction of the loss landscape and further increases moral reasoning performance. This finding shows that explicitly modifying and improving the design of reasoning dynamics offers a promising avenue for advancing pluralistic alignment in LLMs.
%U https://aclanthology.org/2026.aacl-long.260/
%P 5761-5785
Markdown (Informal)
[A Geometric Perspective on Stabilizing Value Conflict Resolution](https://aclanthology.org/2026.aacl-long.260/) (Reddy & Liu, AACL-IJCNLP 2026)
ACL
- Saket Reddy and Andy Liu. 2026. A Geometric Perspective on Stabilizing Value Conflict Resolution. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5761–5785, Hengqin, China. Association for Computational Linguistics.