CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data

• URL: http://arxiv.org/abs/2409.13903v1
• Date: Fri, 20 Sep 2024 21:14:36 GMT
• Title: CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data
• Authors: Zhao Cheng, Diane Wan, Matthew Abueg, Sahra Ghalebikesabi, Ren Yi, Eugene Bagdasarian, Borja Balle, Stefan Mellem, Shawn O'Banion,
• Abstract summary: CI-Bench is a comprehensive benchmark for evaluating the ability of AI assistants to protect personal information during model inference. We present a novel, scalable, multi-step data pipeline for generating natural communications, including dialogues and emails. We formulate and evaluate a naive AI assistant to demonstrate the need for further study and careful training towards personal assistant tasks.
• Score: 7.357348564300953
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Advances in generative AI point towards a new era of personalized applications that perform diverse tasks on behalf of users. While general AI assistants have yet to fully emerge, their potential to share personal data raises significant privacy challenges. This paper introduces CI-Bench, a comprehensive synthetic benchmark for evaluating the ability of AI assistants to protect personal information during model inference. Leveraging the Contextual Integrity framework, our benchmark enables systematic assessment of information flow across important context dimensions, including roles, information types, and transmission principles. We present a novel, scalable, multi-step synthetic data pipeline for generating natural communications, including dialogues and emails. Unlike previous work with smaller, narrowly focused evaluations, we present a novel, scalable, multi-step data pipeline that synthetically generates natural communications, including dialogues and emails, which we use to generate 44 thousand test samples across eight domains. Additionally, we formulate and evaluate a naive AI assistant to demonstrate the need for further study and careful training towards personal assistant tasks. We envision CI-Bench as a valuable tool for guiding future language model development, deployment, system design, and dataset construction, ultimately contributing to the development of AI assistants that align with users' privacy expectations.

Related papers

• Data Analysis in the Era of Generative AI [56.44807642944589]
  This paper explores the potential of AI-powered tools to reshape data analysis, focusing on design considerations and challenges. We explore how the emergence of large language and multimodal models offers new opportunities to enhance various stages of data analysis workflow. We then examine human-centered design principles that facilitate intuitive interactions, build user trust, and streamline the AI-assisted analysis workflow across multiple apps.
  arXiv  Detail & Related papers  (2024-09-27T06:31:03Z)
• IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents [20.460482488872145]
  This paper addresses the challenges of developing interactive agents capable of understanding and executing grounded natural language instructions. We introduce a scalable data collection tool for gathering interactive grounded language instructions within a Minecraft-like environment. We present a Human-in-the-Loop interactive evaluation platform for qualitative analysis and comparison of agent performance.
  arXiv  Detail & Related papers  (2024-07-12T00:07:43Z)
• Automating the Information Extraction from Semi-Structured Interview Transcripts [0.0]
  This paper explores the development and application of an automated system designed to extract information from semi-structured interview transcripts. We present a user-friendly software prototype that enables researchers to efficiently process and visualize the thematic structure of interview data.
  arXiv  Detail & Related papers  (2024-03-07T13:53:03Z)
• Can AI Serve as a Substitute for Human Subjects in Software Engineering Research? [24.39463126056733]
  This vision paper proposes a novel approach to qualitative data collection in software engineering research by harnessing the capabilities of artificial intelligence (AI) We explore the potential of AI-generated synthetic text as an alternative source of qualitative data. We discuss the prospective development of new foundation models aimed at emulating human behavior in observational studies and user evaluations.
  arXiv  Detail & Related papers  (2023-11-18T14:05:52Z)
• Does Collaborative Human-LM Dialogue Generation Help Information Extraction from Human Dialogues? [55.28340832822234]
  Problem-solving human dialogues in real applications can be much more complex than existing Wizard-of-Oz collections. We introduce a human-in-the-loop dialogue generation framework capable of synthesizing realistic dialogues.
  arXiv  Detail & Related papers  (2023-07-13T20:02:50Z)
• AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets [56.052803235932686]
  We propose a novel automatic dataset synthesis approach that can generate both large-scale and high-quality recommendation dialogues. In doing so, we exploit: (i) rich personalized user profiles from traditional recommendation datasets, (ii) rich external knowledge from knowledge graphs, and (iii) the conversation ability contained in human-to-human conversational recommendation datasets.
  arXiv  Detail & Related papers  (2023-06-16T05:27:14Z)
• GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration [97.68234051078997]
  We discuss how Pyserini can be integrated with the Hugging Face ecosystem of open-source AI libraries and artifacts. We include a Jupyter Notebook-based walk through the core interoperability features, available on GitHub. We present GAIA Search - a search engine built following previously laid out principles, giving access to four popular large-scale text collections.
  arXiv  Detail & Related papers  (2023-06-02T12:09:59Z)
• Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision [84.31474052176343]
  Recent AI-assistant agents, such as ChatGPT, rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback to align the output with human intentions. This dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision. We propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision.
  arXiv  Detail & Related papers  (2023-05-04T17:59:28Z)
• CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities [92.79451009324268]
  We present CoAuthor, a dataset designed for revealing GPT-3's capabilities in assisting creative and argumentative writing. We demonstrate that CoAuthor can address questions about GPT-3's language, ideation, and collaboration capabilities. We discuss how this work may facilitate a more principled discussion around LMs' promises and pitfalls in relation to interaction design.
  arXiv  Detail & Related papers  (2022-01-18T07:51:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.