Paper deep dive
Ensemble Debates with Local Large Language Models for AI Alignment
Ephraiem Sarabamoun
Models: DeepSeek-R1-32B, DeepSeek-R1-7B, Mistral-7B, Phi-3-3.8B
Abstract
Abstract:As large language models (LLMs) take on greater roles in high-stakes decisions, alignment with human values is essential. Reliance on proprietary APIs limits reproducibility and broad participation. We study whether local open-source ensemble debates can improve alignmentoriented reasoning. Across 150 debates spanning 15 scenarios and five ensemble configurations, ensembles outperform single-model baselines on a 7-point rubric (overall: 3.48 vs. 3.13), with the largest gains in reasoning depth (+19.4%) and argument quality (+34.1%). Improvements are strongest for truthfulness (+1.25 points) and human enhancement (+0.80). We provide code, prompts, and a debate data set, providing an accessible and reproducible foundation for ensemble-based alignment evaluation.
Tags
Links
PDF not stored locally. Use the link above to view on the source site.
Intelligence
Status: not_run | Model: - | Prompt: - | Confidence: 0%
Entities (0)
Relation Signals (0)
No relation signals yet.
Cypher Suggestions (0)
No Cypher suggestions yet.
Full Text
No full-text extraction is stored for this paper yet.