通过最小贝叶斯风险解码在摘要中实现基于共识和一致性的事实性增强
Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding
AI总结：
提出ConSUM方法，利用最小贝叶斯风险解码建立候选摘要间的共识，并结合与源文档的一致性指标进行重排序，以提升摘要的事实性。
摘要：
提高模型生成摘要的质量，尤其是事实性（摘要相对于源内容的准确性）仍然是一个挑战。虽然重排序可以从多个生成候选中选择最优输出，但它仅限于使用源作为指导，导致摘要不可靠。为了解决这一局限性，我们提出了ConSUM，该方法通过考虑两个因素对候选摘要进行重排序：与源文档的一致性以及与其他候选之间的共识。共识是通过对生成的摘要集进行最小贝叶斯风险（MBR）解码建立的，同时通过使用将摘要与源进行比较的事实性感知指标来确保一致性。严格的测试表明，我们的系统与现有方法具有竞争力，人工评估进一步证实其生成的摘要优于其他系统。我们的代码可在https://github.com/naist-nlp/ConSUM获取。
英文摘要：
Improving the quality of model-generated summaries, especially factuality, the accuracy of a summary with respect to its source content, remains a challenge. While reranking could select the optimal output from multiple generated candidates, it is limited to only using the source as guidance, resulting in unreliable summaries. To address this limitation, we propose ConSUM that reranks candidate summaries by considering two factors: consistency to the source document and consensus among the other candidates. Consensus is established using Minimum Bayes Risk (MBR) decoding over the set of generated summaries, while ensuring consistency by employing factuality-aware metrics that compare the summary against the source. Rigorous testing demonstrates that our system is competitive with existing methods, with human evaluations further confirming that its generated summaries are preferred over those from other systems. Our code is available at https://github.com/naist-nlp/ConSUM .
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。
