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.
- Anthology ID:
- 2026.aacl-long.260
- Volume:
- 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)
- Month:
- November
- Year:
- 2026
- Address:
- Hengqin, China
- Editors:
- Yue Zhang ,Ruifeng Xu ,Ayu Purwarianti ,Tong Rong ,Jun Suzuki
- Venues:
- [AACL](https://aclanthology.org/venues/aacl/) |[IJCNLP](https://aclanthology.org/venues/ijcnlp/)
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5761–5785
- Language:
- URL:
- [https://aclanthology.org/2026.aacl-long.260/](https://aclanthology.org/2026.aacl-long.260/)
- DOI:
- Cite (ACL):
- Saket Reddy and Andy Liu. 2026. A Geometric Perspective on Stabilizing Value Conflict Resolution . InProceedings 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.
- Cite (Informal):
- [A Geometric Perspective on Stabilizing Value Conflict Resolution](https://aclanthology.org/2026.aacl-long.260/) (Reddy & Liu, AACL-IJCNLP 2026)
- PDF:
- [https://aclanthology.org/2026.aacl-long.260.pdf](https://aclanthology.org/2026.aacl-long.260.pdf)