paper-with-me

홈 › Papers

MindScope: Exploring cognitive biases in large language models through Multi-Agent Systems

2024-10-06 · Zhentao Xie, Jiabao Zhao, Yilei Wang, Jinxin Shi, Yanhong Bai, Xingjiao Wu, Liang He

Detecting cognitive biases in large language models (LLMs) is a fascinating task that aims to probe the existing cognitive biases within these models. Current methods for detecting cognitive biases in language models generally suffer from incomplete detection capabilities and a restricted range of detectable bias types. To address this issue, we introduced the 'MindScope' dataset, which distinctively integrates static and dynamic elements. The static component comprises 5,170 open-ended questions spanning 72 cognitive bias categories. The dynamic component leverages a rule-based, multi-agent communication framework to facilitate the generation of multi-round dialogues. This framework is flexible and readily adaptable for various psychological experiments involving LLMs. In addition, we introduce a multi-agent detection method applicable to a wide range of detection tasks, which integrates Retrieval-Augmented Generation (RAG), competitive debate, and a reinforcement learning-based decision module. Demonstrating substantial effectiveness, this method has shown to improve detection accuracy by as much as 35.10% compared to GPT-4. Codes and appendix are available at https://github.com/2279072142/MindScope.

📄 PDF Abstract BibTeX arXiv:2410.04452

Code (1)

2279072142/mindscope 공식 구현

Tasks

RAGRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Exploring Conversational Agents as an Effective Tool for Measuring Cognitive Biases in Decision-Making

2024-01-08 · Stephen Pilli

Heuristics and cognitive biases are an integral part of human decision-making. Automatically detecting a particular cognitive bias could enable intelligent tools to provide better decision-support. Detecting the presence…

Decision Making

A Comprehensive Evaluation of Cognitive Biases in LLMs

2024-10-20 · Simon Malberg, Roman Poletukhin, Carolin M. Schuster, Georg Groh

We present a large-scale evaluation of 30 cognitive biases in 20 state-of-the-art large language models (LLMs) under various decision-making scenarios. Our contributions include a novel general-purpose test framework for…

Decision Making

Blind Spots and Biases: Exploring the Role of Annotator Cognitive Biases in NLP

2024-04-29 · Sanjana Gautam, Mukund Srinath

With the rapid proliferation of artificial intelligence, there is growing concern over its potential to exacerbate existing biases and societal disparities and introduce novel ones. This issue has prompted widespread att…

Decision Making

Cognitive bias in large language models: Cautious optimism meets anti-Panglossian meliorism

2023-11-18 · David Thorstad

Traditional discussions of bias in large language models focus on a conception of bias closely tied to unfairness, especially as affecting marginalized groups. Recent work raises the novel possibility of assessing the ou…

CBEval: A framework for evaluating and interpreting cognitive biases in LLMs

2024-12-04 · Ammar Shaikh, Raj Abhijit Dandekar, Sreedath Panat, Rajat Dandekar

Rapid advancements in Large Language models (LLMs) has significantly enhanced their reasoning capabilities. Despite improved performance on benchmarks, LLMs exhibit notable gaps in their cognitive processes. Additionally…

Decision Making