Demo: TOSense -- What Did You Just Agree to?
Xinzhang Chen, Hassan Ali, Arash Shaghaghi, Salil S. Kanhere, Sanjay Jha

TL;DR
TOSense is a Chrome extension that enables users to ask natural language questions about Terms of Service and receive concise, real-time answers by combining automated content extraction and a lightweight language model pipeline.
Contribution
It introduces a novel system integrating automated ToS crawling, a lightweight language model pipeline, and a synthetic question-answering evaluation method to improve ToS understanding.
Findings
Achieved up to 44.5% accuracy in real-world tests
Effectively extracts ToS content from major platforms
Demonstrates real-time, interactive ToS question answering
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExpert finding and Q&A systems · Topic Modeling · Web Data Mining and Analysis
