Citations from LLM-based RAG systems are supposed to simplify response verification. However, this goal is undermined in cases of citation failure, where a model generates a helpful response, but fails to generate citations to complete evidence. In contrast to previous work, we propose to disentangle this from response failure, where the response itself is flawed, and citing complete evidence is impossible. To address citation failure, this work follows a two-step approach: (1) We study when citation failure occurs and (2) how it can be mitigated efficiently. For step 1, we extend prior work by investigating how the relation between response and evidence affects citation quality. We introduce CITECONTROL, a benchmark that systematically varies this relation to enable the analysis of failure modes. Experiments show that failures increase with relational complexity and suggest that combining citation methods could improve performance, motivating step 2. To study the efficient improvement of LLM citation, we propose CITENTION, a framework integrating generative, attention-based, and retrieval-based methods. Results demonstrate substantial citation improvements on CITECONTROL and in transfer settings. We make our data and code publicly available.

翻译：基于LLM的RAG系统中的引文本应简化回答验证过程。然而，当出现引文失效时——即模型生成了有用的回答，却未能生成指向完整证据的引文——这一目标便受到损害。与先前研究不同，我们主张将引文失效与回答失效（即回答本身存在缺陷，因而无法引用完整证据）进行区分。为解决引文失效问题，本研究采用两步走的方法：（1）探究引文失效的发生条件；（2）研究如何高效缓解该问题。针对第一步，我们通过深入分析回答与证据之间的关系如何影响引文质量，拓展了已有研究。我们提出了CITECONTROL基准，该系统性地改变回答与证据的关系，从而支持失效模式的分析。实验表明，失效率随关系复杂度的增加而上升，并提示结合多种引文方法可能提升性能，这推动了第二步的研究。为探索高效改进LLM引文生成的方法，我们提出了CITENTION框架，该框架整合了生成式、基于注意力机制以及基于检索的方法。实验结果表明，该框架在CITECONTROL基准及迁移场景中均实现了显著的引文质量提升。我们已公开相关数据与代码。