Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
A pipeline trains general-purpose red teaming models by finetuning small LLMs like Qwen3-8B to generate attacks for both seen and unseen adversarial objectives without relying on existing evaluators.
LLMEval-Fair introduces a dynamic, contamination-resistant evaluation framework for LLMs based on a large question bank and validates it via a 30-month study of nearly 60 models showing performance ceilings and hidden contamination issues.
Large reasoning models exhibit reasoning collapse, with accuracy dropping sharply beyond task-specific complexity thresholds in controlled versions of nine classical reasoning tasks using strict validity validators.
Introduces CRAI-MCF, an eight-module framework distilling 217 parameters from 240 projects into a quantitative sufficiency criterion for cross-model LLM comparison grounded in Value Sensitive Design.
citing papers explorer
-
Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia
Mini-Mafia supplies an analytical model logit(p) = v*(m-d) for mafia win probability in LLM role interactions and uses Bayesian inference to estimate per-model parameters that predict tournament results with 76.6% Brier-score improvement over random.
-
Training a General Purpose Automated Red Teaming Model
A pipeline trains general-purpose red teaming models by finetuning small LLMs like Qwen3-8B to generate attacks for both seen and unseen adversarial objectives without relying on existing evaluators.
-
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models
LLMEval-Fair introduces a dynamic, contamination-resistant evaluation framework for LLMs based on a large question bank and validates it via a 30-month study of nearly 60 models showing performance ceilings and hidden contamination issues.
-
Empirical Evidence of Complexity-Induced Limits in Large Language Models on Finite Discrete State-Space Problems with Explicit Validity Constraints
Large reasoning models exhibit reasoning collapse, with accuracy dropping sharply beyond task-specific complexity thresholds in controlled versions of nine classical reasoning tasks using strict validity validators.
-
Human-aligned AI Model Cards with Weighted Hierarchy Architecture
Introduces CRAI-MCF, an eight-module framework distilling 217 parameters from 240 projects into a quantitative sufficiency criterion for cross-model LLM comparison grounded in Value Sensitive Design.