arXiv Open Access 2026

Care-Conditioned Neuromodulation for Autonomy-Preserving Supportive Dialogue Agents

Shalima Binta Manir Tim Oates
Lihat Sumber

Abstrak

Large language models deployed in supportive or advisory roles must balance helpfulness with preservation of user autonomy, yet standard alignment methods primarily optimize for helpfulness and harmlessness without explicitly modeling relational risks such as dependency reinforcement, overprotection, or coercive guidance. We introduce Care-Conditioned Neuromodulation (CCN), a state-dependent control framework in which a learned scalar signal derived from structured user state and dialogue context conditions response generation and candidate selection. We formalize this setting as an autonomy-preserving alignment problem and define a utility function that rewards autonomy support and helpfulness while penalizing dependency and coercion. We also construct a benchmark of relational failure modes in multi-turn dialogue, including reassurance dependence, manipulative care, overprotection, and boundary inconsistency. On this benchmark, care-conditioned candidate generation combined with utility-based reranking improves autonomy-preserving utility by +0.25 over supervised fine-tuning and +0.07 over preference optimization baselines while maintaining comparable supportiveness. Pilot human evaluation and zero-shot transfer to real emotional-support conversations show directional agreement with automated metrics. These results suggest that state-dependent control combined with utility-based selection is a practical approach to multi-objective alignment in autonomy-sensitive dialogue.

Topik & Kata Kunci

Penulis (2)

S

Shalima Binta Manir

T

Tim Oates

Format Sitasi

Manir, S.B., Oates, T. (2026). Care-Conditioned Neuromodulation for Autonomy-Preserving Supportive Dialogue Agents. https://arxiv.org/abs/2604.01576

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓