A Persona-Based Neural Conversation Model
read the original abstract
We present persona-based models for handling the issue of speaker consistency in neural response generation. A speaker model encodes personas in distributed embeddings that capture individual characteristics such as background information and speaking style. A dyadic speaker-addressee model captures properties of interactions between two interlocutors. Our models yield qualitative performance improvements in both perplexity and BLEU scores over baseline sequence-to-sequence models, with similar gains in speaker consistency as measured by human judges.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation
Multi-agent LLM simulations with trait-conditioned agents and a reinforcement-learning orchestrator show heterogeneous teams and dynamic trait selection outperform static configurations in simulated legal argumentation.
-
Deception Strategies and Threats for Online Discussions
A review of historical deception strategies in communication and their application to current online threats from social bots and disinformation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.