发表机构
University of California Santa Barbara; Georgia Institute of Technology（加利福尼亚大学圣巴巴拉分校; 佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对检索增强问答中证据选择问题，将其转化为QUBO问题构建能量函数，平衡多种因素选择证据段落，再由下游语言模型生成答案。在HotpotQA上评估，该方法性能与基于LLM的选择器相当，为RAG管道提供新思路。
AI 中文摘要
检索增强问答依赖于选择共同支持答案生成的证据段落。许多RAG管道依赖于top-k排名，尽管多跳问题通常需要满足多个信息需求的互补证据。基于LLM的选择器将检索视为集合选择来解决此问题，但在中间阶段使用LLM成本高且难以扩展。本文将证据选择公式化为二次无约束二元优化（QUBO）问题，构建能量函数平衡多种因素。所选段落再传递给下游语言模型生成答案。在HotpotQA上评估了QUBO选择器，结果表明多跳证据选择可转化为离散优化，为RAG管道开辟了一条路径。
英文摘要
Retrieval-augmented question answering depends on selecting evidence passages that jointly support answer generation. However, many RAG pipelines rely on top-\(k\) ranking, where passages are selected mainly by individual relevance scores, even though multi-hop questions often require complementary evidence satisfying multiple information requirements. Recent LLM-based selectors address this by treating retrieval as set selection, but using an LLM for this intermediate stage can be costly and difficult to scale. In this work, we formulate evidence selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem. Given a question, candidate passages, and decomposed information requirements, our method constructs an energy function that balances relevance, requirement coverage, support strength, redundancy, complementarity, and compactness. Low-energy solutions correspond to compact evidence subsets that cover the needed requirements while avoiding unnecessary or repetitive context. The selected passages are then passed to a downstream language model for answer generation, separating combinatorial evidence selection from semantic answer generation. We evaluate the proposed QUBO selector on HotpotQA and compare it with LLM-based set selectors and non-LLM baselines including BM25, relevance top-\(k\), maximal marginal relevance, hybrid lexical--semantic ranking, greedy coverage, and random selection. The QUBO selector achieves competitive exact-match and token-F1 performance relative to LLM-based selectors while providing a solver-compatible formulation for structured evidence selection. These results suggest that multi-hop evidence selection can be cast as discrete optimization, opening a path toward RAG pipelines where LLMs are reserved for semantic processing and answer generation, while context selection is handled by Ising/QUBO-compatible solvers.
