当检索前思考有害时：用于自适应知识图谱检索的TraceBound诊断
When Thinking Before Retrieval Hurts: TraceBound Diagnostics for Adaptive Knowledge-Graph Retrieval
浏览论文内容
中文总结 AI 辅助
研究知识图谱自适应检索中“检索前思考”有害问题，引入TraceBound诊断协议，它能暴露查询配置文件等。实验表明虽改善可检查性，但降低检索质量，通过分析定位退化原因，指出应将其作为动作选择控制问题评估。
中文摘要 AI 辅助
自适应检索有望通过让控制器进行搜索、检查邻域、修正动作并在证据充分时停止，使知识图谱问答更稳健。我们通过引入TraceBound来研究这一前提，它是一种用于富含文本的知识图谱上的ARK风格检索器的轻量级、基于配置文件和跟踪条件的诊断协议。TraceBound在检索前暴露紧凑的查询配置文件，在出现可观察到的失败症状后发出短跟踪提示，并记录轨迹计数器，同时保持图数据、工具、黄金标签和排名指标不变。在STaRK验证集和留出子集中，额外的条件改善了可检查性，但在开放权重控制器下持续降低了检索质量。配对轨迹分析将退化定位到重复调用、零结果调用和错误分配的探索预算，而更严格的交互预算缩短了轨迹但未修复策略。结果诊断出常见的失败模式，即“检索前思考”必须作为动作选择的控制问题来评估，而不是作为提示格式的改变。
英文摘要
Adaptive retrieval promises to make knowledge-graph question answering more robust by letting a controller search, inspect neighborhoods, revise actions, and stop when evidence is sufficient. We study this premise by introducing TraceBound, a lightweight profile- and trace-conditioned diagnostic protocol for an ARK-style retriever on text-rich knowledge graphs. TraceBound exposes a compact query profile before retrieval, issues short trace hints after observable failure symptoms, and logs trajectory counters, while keeping graph data, tools, gold labels, and ranking metrics fixed. Across STaRK validation and held-out subsets, the added conditioning improves inspectability but consistently reduces retrieval quality under open-weight controllers. Paired trajectory analysis localizes the degradation to repeated calls, zero-result calls, and misallocated exploration budget, while stricter interaction budgets shorten trajectories without repairing the policy. The result diagnoses the common failure mode in that "thinking before retrieval'' must be evaluated as a control problem over action selection, not as a prompt-format change.
发表机构
- ETH Zürich（苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。
