Research map / Multi-agent systems and games / Human-AI and goal-conditioned
ALOHA: Artificial Learning of Human Attributes for Dialogue Agents
Aaron W. Li, Veronica Jiang, Steven Y. Feng, Julia Sprague, Wei Zhou, Jesse Hoey
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 HLA-guided character modeling and negative character sampling instead of uniform character sampling | ALOHA-BERT versus Uniform Model · Five evaluation characters | Hits@1/20 | Improved |
| Use HLA-guided character modeling and negative character sampling instead of uniform character sampling | ALOHA-Poly versus Uniform Model · Five evaluation characters | Hits@1/20 | Improved |
| Use ALOHA character-style recovery rather than the BERT bi-ranker baseline | ALOHA-BERT · Five evaluation characters | Hits@1/20 | Improved |
| Use ALOHA character-style recovery rather than the Poly-encoder baseline | ALOHA-Poly · Five evaluation characters | Hits@1/20 | Improved |
| Use HLA-based ALOHA responses rather than responses from the Uniform Model | ALOHA · Five evaluation characters | correlation with human Hits@1/20: 0.047; 0.4149; 0.5468 | Improved |
| Use ALOHA rather than human evaluators | ALOHA · Two of five evaluation characters | Hits@1/20 | Mixed |
Closest papers by meaning
- Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning (NeurIPS 2025 · similarity 0.85)
- CharacterBench: Benchmarking Character Customization of Large Language Models (AAAI 2025 · similarity 0.84)
- CoSER: Coordinating LLM-Based Persona Simulation of Established Roles (ICML 2025 · similarity 0.83)
- Human Simulacra: Benchmarking the Personification of Large Language Models (ICLR 2025 · similarity 0.83)
- Codifying Character Logic in Role-Playing (NeurIPS 2025 · similarity 0.83)
- Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward (NeurIPS 2025 · similarity 0.82)
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.
