Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers
cs.HC, cs.AI
Submitted: 2025-10-01
Updated: 2026-10-28
License: http://creativecommons.org/licenses/by/4.0/
The gist: AI answer engines are a relatively new kind of information search tool: rather than returning a ranked list of documents, they generate an answer to a search question with inline citations to sources.
Terminology
Abstract
AI answer engines are a relatively new kind of information search tool: rather than returning a ranked list of documents, they generate an answer to a search question with inline citations to sources. But reading the cited sources is costly, and citation links themselves offer little guidance about what evidence they contain. We present attribution gradients, a technique to boost the informativeness of citations by consolidating scent and information prey in place. Its first feature is bringing evidence counts, supporting/contradictory excerpts, links to sources, and contextual explanations into one place. Its second feature is the ability to unravel second-degree citations in place. In a lab study, we demonstrate usage of the full gradient in a critical reading task and its support for deep engagement that increased the depth of what readers took away from the sources versus a standard citation and document QA design.
Sources
- OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
- The Semantic Scholar Open Data Platform
- Search Engines Post-ChatGPT: How Generative Artificial Intelligence Could Make Search Less Reliable
- An Audit on the Perspectives and Challenges of Hallucinations in NLP
- Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems