AgentProp-Bench shows substring judging agrees with humans at kappa=0.049, LLM ensemble at 0.432, bad-parameter injection propagates with ~0.62 probability, rejection and recovery are independent, and a runtime fix cuts hallucinations 23pp on GPT-4o-mini but not Gemini-2.0-Flash.
Rankers, judges, and assis- tants: Towards understanding the interplay of llms in information retrieval evaluation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2roles
background 2representative citing papers
The thesis identifies theoretical, empirical, and conceptual flaws in offline fairness measures for recommender systems and contributes new evaluation methods and practical guidelines.
citing papers explorer
-
Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench
AgentProp-Bench shows substring judging agrees with humans at kappa=0.049, LLM ensemble at 0.432, bad-parameter injection propagates with ~0.62 probability, rejection and recovery are independent, and a runtime fix cuts hallucinations 23pp on GPT-4o-mini but not Gemini-2.0-Flash.
-
Offline Evaluation Measures of Fairness in Recommender Systems
The thesis identifies theoretical, empirical, and conceptual flaws in offline fairness measures for recommender systems and contributes new evaluation methods and practical guidelines.