Llm As Judge
3 items across the graph — tagged with Llm As Judge.
From the graph · 3
repo
DaoyuanLi2816/pairjudge
→repoPairwise LLM judges (A/B/tie): budget-aware multi-turn packing, position-bias correction, pseudo-label distillation. Generalized from the 4th-place (gold) solut…
johnsonfarmsus/openwebui-ab-mcts-pipeline
→repoOpen WebUI Logic Tree Multi-Model LLM Project - Advanced AI reasoning with Sakana AI's AB-MCTS and sophisticated multi-model collaboration
nomograph/jig
→Agent-shape testing harness that measures how an LLM-driven agent uses a tool's CLI, scored by an LLM judge.