A post-training framework with persona-specific LoRA experts and a situation-aware router improves LLM emotional responses, but the evidence on preserving general ability is undercut by missing base-model comparisons.
Findings of the Association for Computational Linguistics: EMNLP 2023, 6516--6528 (Association for Computational Linguistics)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions
A post-training framework with persona-specific LoRA experts and a situation-aware router improves LLM emotional responses, but the evidence on preserving general ability is undercut by missing base-model comparisons.