Research map / Large language models / Language, safety and interpretability
A Disentangled-Attention Based Framework with Persona-Aware Prompt Learning for Dialogue Generation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the proposed framework instead of P² Bot | Persona-grounded dialogue generation · PERSONA-CHAT original test | BLEU: 26.90 -> 28.54 | Helped |
| Use the proposed framework instead of P² Bot | Persona-grounded dialogue generation · PERSONA-CHAT original test | F1: 19.67 -> 19.84 | Helped |
| Use the proposed framework instead of P² Bot | Persona-grounded dialogue generation · PERSONA-CHAT revised test | BLEU: 26.25 -> 29.68 | Helped |
| Use the proposed framework instead of P² Bot | Persona-grounded dialogue generation · PERSONA-CHAT revised test | Consistency: 1.325 -> 1.527 | Helped |
| Add Sequential Persona Selection (ablation) | Proposed dialogue generation framework · PERSONA-CHAT revised data | BLEU: 28.20 -> 29.68 | Helped |
| Add persona-aware prompting (ablation) | Proposed dialogue generation framework · PERSONA-CHAT revised data | BLEU: 28.76 -> 29.68 | Helped |
| Add the Disentangled-Attention decoder (ablation) | Proposed dialogue generation framework · PERSONA-CHAT revised data | BLEU: 28.45 -> 29.68 | Helped |
| Add the Persona-aware adapter (ablation) | Disentangled-Attention decoder · PERSONA-CHAT revised data | BLEU: 27.38 -> 29.68 | Helped |
| Add the Context-aware adapter (ablation) | Disentangled-Attention decoder · PERSONA-CHAT revised data | BLEU: 28.65 -> 29.68 | Helped |
| Add the Persona-Context-aware adapter (ablation) | Disentangled-Attention decoder · PERSONA-CHAT revised data | BLEU: 27.87 -> 29.68 | Helped |
| Add A*-like keyword heuristics (ablation) | Proposed dialogue generation framework · PERSONA-CHAT revised data | BLEU: 28.93 -> 29.68 | Helped |
Closest papers by meaning
- Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward (NeurIPS 2025 · similarity 0.86)
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models (NeurIPS 2026 · similarity 0.86)
- PersonaVLM: Long-Term Personalized Multimodal LLMs (CVPR 2026 · similarity 0.85)
- PICLe: Eliciting Diverse Behaviors from Large Language Models with Persona In-Context Learning (ICML 2024 · similarity 0.85)
- Who's asking? User personas and the mechanics of latent misalignment (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.