TermSight: Making Service Contracts Approachable

📅 2025-06-14
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Terms of Service (ToS) agreements are ubiquitous yet notoriously inaccessible, riddled with ambiguous legal jargon that impedes user comprehension and undermines informed consent. To address this, we introduce TermSight—the first intelligent ToS reading interface that jointly visualizes power asymmetries, clause relevance, and simplification levels. TermSight integrates NLP-driven clause classification and simplification, interactive information visualization, context-aware definition generation, and scenario-based explanations to realize an AI-augmented, user-centered reading strategy. A within-subjects user study (N=20) demonstrates that TermSight significantly reduces cognitive load during ToS reading, increases users’ willingness to engage with legal texts, and—critically—reveals a novel human-AI collaboration paradigm for interpreting legal documents. This work advances accessible legal technology by bridging computational linguistics, human-computer interaction, and digital rights advocacy.

Technology Category

Application Category

📝 Abstract
Terms of Service (ToS) are ubiquitous, legally binding contracts that govern consumers' digital interactions. However, ToS are not designed to be read: they are filled with pages of ambiguous and complex legal terminology that burden potential users. We introduce TermSight, an intelligent reading interface designed to make ToS more approachable. TermSight offers visual summaries that highlight the relevance and power balance of information in a ToS. TermSight also categorizes and simplifies information within the ToS into concise plain-language summaries. To aid in reading the original text, TermSight offers contextualized definitions and scenarios for unfamiliar phrases. Our within-subjects evaluation of TermSight (N=20) revealed that TermSight significantly reduced the difficulty of reading ToS and increased participants' willingness to do so. We also observed emerging strategies that participants took when interacting with AI-powered features that highlight the diverse ways that TermSight assisted ToS reading.
Problem

Research questions and friction points this paper is trying to address.

Simplifying complex legal terms in ToS
Improving readability of service contracts
Enhancing user engagement with ToS
Innovation

Methods, ideas, or system contributions that make the work stand out.

Visual summaries highlighting relevance and power balance
Categorizes and simplifies ToS into plain-language summaries
Provides contextualized definitions and scenarios for phrases
🔎 Similar Papers
No similar papers found.