Demo: TOSense -- What Did You Just Agree to?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xinzhang, Ali, Hassan, Shaghaghi, Arash, Kanhere, Salil S., Jha, Sanjay
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918110278189056
author Chen, Xinzhang
Ali, Hassan
Shaghaghi, Arash
Kanhere, Salil S.
Jha, Sanjay
author_facet Chen, Xinzhang
Ali, Hassan
Shaghaghi, Arash
Kanhere, Salil S.
Jha, Sanjay
contents Online services often require users to agree to lengthy and obscure Terms of Service (ToS), leading to information asymmetry and legal risks. This paper proposes TOSense-a Chrome extension that allows users to ask questions about ToS in natural language and get concise answers in real time. The system combines (i) a crawler "tos-crawl" that automatically extracts ToS content, and (ii) a lightweight large language model pipeline: MiniLM for semantic retrieval and BART-encoder for answer relevance verification. To avoid expensive manual annotation, we present a novel Question Answering Evaluation Pipeline (QEP) that generates synthetic questions and verifies the correctness of answers using clustered topic matching. Experiments on five major platforms, Apple, Google, X (formerly Twitter), Microsoft, and Netflix, show the effectiveness of TOSense (with up to 44.5% accuracy) across varying number of topic clusters. During the demonstration, we will showcase TOSense in action. Attendees will be able to experience seamless extraction, interactive question answering, and instant indexing of new sites.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00659
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Demo: TOSense -- What Did You Just Agree to?
Chen, Xinzhang
Ali, Hassan
Shaghaghi, Arash
Kanhere, Salil S.
Jha, Sanjay
Cryptography and Security
Computation and Language
Online services often require users to agree to lengthy and obscure Terms of Service (ToS), leading to information asymmetry and legal risks. This paper proposes TOSense-a Chrome extension that allows users to ask questions about ToS in natural language and get concise answers in real time. The system combines (i) a crawler "tos-crawl" that automatically extracts ToS content, and (ii) a lightweight large language model pipeline: MiniLM for semantic retrieval and BART-encoder for answer relevance verification. To avoid expensive manual annotation, we present a novel Question Answering Evaluation Pipeline (QEP) that generates synthetic questions and verifies the correctness of answers using clustered topic matching. Experiments on five major platforms, Apple, Google, X (formerly Twitter), Microsoft, and Netflix, show the effectiveness of TOSense (with up to 44.5% accuracy) across varying number of topic clusters. During the demonstration, we will showcase TOSense in action. Attendees will be able to experience seamless extraction, interactive question answering, and instant indexing of new sites.
title Demo: TOSense -- What Did You Just Agree to?
topic Cryptography and Security
Computation and Language
url https://arxiv.org/abs/2508.00659