mlsanityData to 7 Oct 2026

Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots

arXiv 2410.11876 ↗First posted 10 Oct 2024cs.HC cs.AI cs.CRcited by 16

Not on the map. Why?

Abstract (arXiv)

The proliferation of LLM-based conversational agents has resulted in excessive disclosure of identifiable or sensitive information. However, existing technologies fail to offer perceptible control or account for users' personal preferences about privacy-utility tradeoffs due to the lack of user involvement. To bridge this gap, we designed, built, and evaluated Rescriber, a browser extension that supports user-led data minimization in LLM-based conversational agents by helping users detect and sanitize personal information in their prompts. Our studies (N=12) showed that Rescriber helped users reduce unnecessary disclosure and addressed their privacy concerns. Users' subjective perceptions of the system powered by Llama3-8B were on par with that by GPT-4o. The comprehensiveness and consistency of the detection and sanitization emerge as essential factors that affect users' trust and perceived protection. Our findings confirm the viability of smaller-LLM-powered, user-facing, on-device privacy controls, presenting a promising approach to address the privacy and trust challenges of AI.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 23 of its 68 references that are in the map. First posted on arXiv 10 Oct 2024.

Builds on

23 of 68 references.

References · 23

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  4. 2020Extracting Training Data from Large Language Modelscited by 2,144
  5. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  6. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Modelscited by 424
  7. 2023Scalable Extraction of Training Data from (Production) Language Modelscited by 415
  8. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  9. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  10. 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 309
  11. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 218
  12. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 194
11 more
  1. 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Actioncited by 161
  2. 2021Counterfactual Memorization in Neural Language Modelscited by 155
  3. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
  4. 2023"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agentscited by 60
  5. 2023Reducing Privacy Risks in Online Self-Disclosures with Language Modelscited by 47
  6. 2024Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wildcited by 43
  7. 2020Operationalizing the Legal Principle of Data Minimization for Personalizationcited by 19
  8. 2024Granular Privacy Control for Geolocation with Vision Language Modelscited by 19
  9. 2024Human-Centered Privacy Research in the Age of Large Language Modelscited by 9
  10. 2024The Boy Who Survived: Removing Harry Potter from an LLM is harder than reportedcited by 4
  11. 2018Understanding Software Developers' Approach towards Implementing Data Minimizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 7.

16 papers.

Sort:

By area:

  1. 2025Position: Privacy Is Not Just Memorization!cited by 15
  2. 2025Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigationcited by 11
  3. 2025Operationalizing Data Minimization for Privacy-Preserving LLM Promptingcited by 8
  4. 2025How do we measure privacy in text? A survey of text anonymization metricscited by 5
  5. 2025Can Large Language Models Really Recognize Your Name?cited by 4
  6. 2025Not My Agent, Not My Boundary? Elicitation of Personal Privacy Boundaries in AI-Delegated Information Sharingcited by 3
  7. 2026Privasis: Synthesizing the Largest "Public" Private Dataset from Scratchcited by 3
  8. 2025Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inferencecited by 2
  9. 2026GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistantcited by 1
  10. 2025One Size Fits All? A Modular Adaptive Sanitization Kit (MASK) for Customizable Privacy-Preserving Phone Scam Detectioncited by 0
  11. 2025SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharingcited by 0
  12. 2026From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Managementcited by 0
4 more
  1. 2026Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agentscited by 0
  2. 2026BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelinescited by 0
  3. 2026Rethinking Agent Security as a Networking Problemcited by 0
  4. 2026GuardianAgent: Policy-Conditioned Risk-Adaptive Anonymization with Verified Adversarial Escalationcited by 0