arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.08696cs.LGcs.AI
收藏

固定LLM预算下的反事实追索的智能搜索

Agentic Search for Counterfactual Recourse under Fixed LLM Budgets

RIKEN Center for Advanced Intelligence Project(日本RIKEN高级智能项目中心)

Yasuo Tabei

AI总结:

提出Comp-MCTS框架,在固定LLM调用预算下,通过树搜索最大化生成唯一且经oracle验证的反事实,平衡数量与质量。

摘要:

反事实追索旨在提供可操作的特征变化,以改变预测模型做出的不利决策。在实践中,受影响的个体通常受益于多个可行的替代方案,而非单一的最优解释。产生此类替代方案的一种自然方式是提示大语言模型(LLMs)。然而,提示引入了一个实际约束:LLM调用的数量通常是主要的计算和经济成本。对多个替代方案的需求以及这一成本约束共同将问题从寻找单个高质量反事实转变为在固定LLM调用预算下高效生成一组经oracle验证的反事实。在这项工作中,我们将LLM智能体设置中的反事实追索生成作为固定预算搜索问题进行研究,并提出了Comp-MCTS,一个智能体树搜索框架,该框架在此预算下最大化唯一、经oracle验证的反事实的产出,同时保持有利的数量-质量权衡。Comp-MCTS通过基于LLM的提议生成、oracle验证和压缩引导剪枝,在无训练、仅oracle的设置中将预算分配给新颖的干预方向。在四个真实世界表格数据集上的实验表明,Comp-MCTS在唯一、经oracle验证的反事实产出方面显著优于单候选LATS风格基线,并且与更强的多候选变体相比,提供了有利的数量-质量-效率权衡:在四个数据集中的三个上,以相似或更低的oracle评估成本获得相当或更高的产出,同时具有有竞争力的接近性、稀疏性和新颖性。

英文摘要:

Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable decision made by a predictive model. In practice, affected individuals often benefit from multiple feasible alternatives rather than a single optimal explanation. A natural way to produce such alternatives is to prompt large language models (LLMs). However, prompting incurs a practical constraint: the number of LLM calls is often the dominant computational and economic cost. Together, the need for multiple alternatives and this cost constraint shift the problem from finding a single high-quality counterfactual to efficiently generating a set of oracle-validated counterfactuals under a fixed LLM-call budget. In this work, we study counterfactual recourse generation in the LLM-agentic setting as a fixed-budget search problem and propose Recourse Monte Carlo Tree Search (ReCo-MCTS), an agentic tree-search framework that aims to increase the yield of unique, oracle-validated counterfactuals under this budget while accounting for the extent of the required changes. ReCo-MCTS combines LLM-based multi-candidate generation, constraint checking, black-box oracle evaluation, and UCT-guided tree search to accumulate valid counterfactuals under a fixed LLM-call budget. On four real-world tabular datasets, ReCo-MCTS returns more counterfactuals than the evaluated baselines in our main comparison under the specified resource limits, with trade-offs in the extent of the required changes.

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。

↑