Problem
Research questions and friction points this paper is trying to address.
search agents
lazy grounding
factual evidence
misinformation
Lazy Grounding: Attacking Search Agents with Factual Evidence
🤖 AI Summary
研究解决了搜索代理因依赖检索而易受误导的问题，通过展示事实证据也能导致代理采纳不相关答案的现象，提出并验证了懒惰接地的概念。
📝 Abstract
Search agents reduce hallucination by grounding answers in retrieved web evidence. Yet reliance on retrieval also creates an attack surface: poisoned corpora with false or malicious documents can cause agents to reproduce misinformation. We show that falsehood is not necessary -- a search agent can be misled by factual evidence for a nearby question, adopting that nearby answer even when it does not answer the current question. We call this failure lazy grounding. We expose lazy grounding using nearby evidence from answer-changing rewrites of benchmark questions. Each document truthfully supports a neighboring rewritten question, but is surfaced for the original question. Across 12 model-benchmark pairs, nearby evidence reduces accuracy by 5.9 points on average and by up to 17.3 points, while inducing nearby-answer adoption in every setting. The effect is stronger when nearby evidence appears later or is more answer-shaped. Our results show that robust search agents must defend against not only misinformation but also the misapplication of factual evidence. The code is publicly available at https://github.com/frankyzha/lazy-grounding.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Lazy Grounding
Search Agents
Factual Evidence
Misinformation Defense
🔎 Similar Papers
No similar papers found.
