主动概念学习中的大胆猜测与温和猜测
Wild Guesses and Mild Guesses in Active Concept Learning
AI总结:
本文研究了主动概念学习中EIG与PTS策略的权衡,发现EIG在复杂规则中有效但对简单规则表现欠佳,而PTS通过安全查询维持提案有效性,提升收敛速度。
摘要:
人类的概念学习通常是主动的:学习者选择哪些实例进行查询或测试,以减少对潜在规则或类别的不确定性。主动概念学习必须在查询的信息量与生成和评分假设的稳定性之间取得平衡。我们研究了这种权衡,采用一种神经符号贝叶斯学习器,其假设是大型语言模型(LLM)提出并经贝叶斯更新重新加权的可执行程序。我们比较了理性主动学习者(选择查询以最大化近似预期信息增益(EIG))和类人正测试策略(PTS),后者查询在当前最佳假设下被预测为正的实例。在经典的数字游戏中,EIG在需要证伪时有效(例如复合或例外规则),但在简单概念上表现欠佳。我们发现这种失败是由于EIG策略与LLM提案分布之间的支持不匹配:高度诊断性的边界查询使后验向生成无效或过于特定的程序的区域偏移,导致粒子近似中的支持不匹配陷阱。PTS虽然信息次优,但通过选择“安全”的查询来维持提案有效性,从而在简单规则上更快收敛。我们的结果表明,'确认偏见'可能不是认知错误,而是为在人类思维中典型的稀疏、开放性假设空间中保持可推断性的理性适应。
英文摘要:
Human concept learning is typically active: learners choose which instances to query or test in order to reduce uncertainty about an underlying rule or category. Active concept learning must balance informativeness of queries against the stability of the learner that generates and scores hypotheses. We study this trade-off in a neuro-symbolic Bayesian learner whose hypotheses are executable programs proposed by a large language model (LLM) and reweighted by Bayesian updating. We compare a Rational Active Learner that selects queries to maximize approximate expected information gain (EIG) and the human-like Positive Test Strategy (PTS) that queries instances predicted to be positive under the current best hypothesis. Across concept-learning tasks in the classic Number Game, EIG is effective when falsification is necessary (e.g., compound or exception-laden rules), but underperforms on simple concepts. We trace this failure to a support mismatch between the EIG policy and the LLM proposal distribution: highly diagnostic boundary queries drive the posterior toward regions where the generator produces invalid or overly specific programs, yielding a support-mismatch trap in the particle approximation. PTS is information-suboptimal but tends to maintain proposal validity by selecting "safe" queries, leading to faster convergence on simple rules. Our results suggest that "confirmation bias" may not be a cognitive error, but rather a rational adaptation for maintaining tractable inference in the sparse, open-ended hypothesis spaces characteristic of human thought.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。