llm-ensemble

The paper presents a nine-voter ensemble system using error-independent LLMs for harmful content detection in German social media, achieving first place in GermEval 2026 shared task across four subtasks by addressing class imbalance.

This paper introduces PROBE, a multi-stage pipeline for diagnosing 802.11 packet captures that combines deterministic normalization, multi-run ensemble, and a verdict-aware evidence framework to produce reliable and calibrated diagnoses, outperforming single-pass LLM analysis and naive ensemble voting.

Proposes a framework for selecting complementary LLMs as proposers in ensemble systems, reformulating proposer selection as a combinatorial problem and exploring greedy algorithms for efficient performance-cost trade-offs.