GRATR: Zero-Shot Evidence Graph Retrieval-Augmented Trustworthiness Reasoning

📅 2024-08-22
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the challenge of individual credibility inference in incomplete-information multi-agent games, this paper proposes a zero-shot graph-augmented retrieval framework. It dynamically constructs trust graphs, performs multi-hop evidence-chain retrieval, and leverages large language model (LLM) prompting—without fine-tuning—to enable interpretable and robust intent analysis. The core contribution is the first zero-shot, graph-structured evidence retrieval mechanism that tightly couples trust modeling with multi-source evidence-chain reasoning, substantially enhancing interpretability and hallucination resistance. Experiments demonstrate a 50.5% improvement in inference accuracy on the *Werewolf* game benchmark and a 30.6% reduction in hallucination rate. On a real-world U.S. election Twitter dataset, accuracy increases by 10.4%, validating strong cross-domain generalizability and practical applicability.

Technology Category

Application Category

📝 Abstract
Trustworthiness reasoning aims to enable agents in multiplayer games with incomplete information to identify potential allies and adversaries, thereby enhancing decision-making. In this paper, we introduce the graph retrieval-augmented trustworthiness reasoning (GRATR) framework, which retrieves observable evidence from the game environment to inform decision-making by large language models (LLMs) without requiring additional training, making it a zero-shot approach. Within the GRATR framework, agents first observe the actions of other players and evaluate the resulting shifts in inter-player trust, constructing a corresponding trustworthiness graph. During decision-making, the agent performs multi-hop retrieval to evaluate trustworthiness toward a specific target, where evidence chains are retrieved from multiple trusted sources to form a comprehensive assessment. Experiments in the multiplayer game emph{Werewolf} demonstrate that GRATR outperforms the alternatives, improving reasoning accuracy by 50.5% and reducing hallucination by 30.6% compared to the baseline method. Additionally, when tested on a dataset of Twitter tweets during the U.S. election period, GRATR surpasses the baseline method by 10.4% in accuracy, highlighting its potential in real-world applications such as intent analysis.
Problem

Research questions and friction points this paper is trying to address.

Credibility Assessment
Decision Making
Game Theory
Innovation

Methods, ideas, or system contributions that make the work stand out.

GRATR
Evidence-based Reasoning
Human Behavior Analysis
Y
Ying Zhu
Nanjing University of Information Science and Technology
S
Shengchang Li
The University of Melbourne
Z
Ziqian Kong
Hangzhou Dianzi University
Q
Qiang Yang
Nanjing University of Information Science and Technology
P
Peilan Xu
Nanjing University of Information Science and Technology