This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
Improving LLM -as-a-judge inference with the judgment distribution
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Large-scale study of 21 LLM-as-a-Judge models shows exact-match agreement overstates reliability, rankings shift across benchmarks, and high consistency can mask position bias.
LLM ranking reliability for prioritization tasks can be assessed via coefficient of consistency ζ (intra-run circular triads) and Kendall's τ (inter-run distance), with three leading models showing distinct consistency profiles on homelessness allocation and ED triage.
citing papers explorer
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias
Large-scale study of 21 LLM-as-a-Judge models shows exact-match agreement overstates reliability, rankings shift across benchmarks, and high consistency can mask position bias.
-
Can LLMs Rank? A Tale of Triads and Triage
LLM ranking reliability for prioritization tasks can be assessed via coefficient of consistency ζ (intra-run circular triads) and Kendall's τ (inter-run distance), with three leading models showing distinct consistency profiles on homelessness allocation and ED triage.