arXiv cs.AI· Hita Kambhamettu, Alyssa Hwang, Philippe Laban, Andrew Head·· 14 小时前AI 评分31
Attribution Gradients：为 AI 答案引用提供可展开的证据梯度
Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers
AI 导读
研究者提出 attribution gradients 技术，将证据计数、支持/反驳摘录、来源链接与上下文解释集中到一处，并支持就地展开二级引用，以提升 AI 答案引擎引用的信息量。在一项实验室研究中，该完整梯度被用于批判性阅读任务，相比标准引用与文档 QA 设计，读者从来源中获得的收获深度有所增加。
正文 · 原文
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.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.00361 [cs.HC] |
| (or arXiv:2510.00361v3 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2510.00361 arXiv-issued DOI via DataCite |
Submission history
From: Hita Kambhamettu [view email]
[v1]
Wed, 1 Oct 2025 00:07:28 UTC (1,882 KB)
[v2]
Fri, 3 Apr 2026 00:42:58 UTC (1,262 KB)
[v3]
Wed, 28 Oct 2026 23:22:47 UTC (1,123 KB)
来源：arXiv cs.AI · arxiv.org