解决科学论断验证中证据混淆难题，提升判断准确率。
HNR-DAC: Hard-Negative Reranking and Distribution-Aligned Classification for Scientific Claim Verification
- 两阶段框架：先重排难例，再对齐分布分类
- 在NLPCC任务中达97.21%的Hit@3和95.79%宏F1
- 适合需要高精度科学论断验证的研究者
针对引用论文中的科学论断验证，需预测论断与论文的关系并识别支持该判断的段落。该任务面临两大挑战：同篇论文内的干扰段落常与真实证据相似，而基于黄金证据训练的分类器在推理时需处理检索到的证据。我们提出HNR-DAC，一个两阶段框架，使每个阶段均在实际遇到的场景下训练。硬负样本重排（HNR）利用基础重排器对非黄金段落的得分，量化证据混淆程度，并将黄金证据与最易混淆候选项进行对比。分布对齐分类（DAC）在由相同冻结的HNR生成的前1个段落上训练，同时以HNR的前3个段落标识作为证据输出。在NLPCC 2026任务10赛道2中，最终配置取得97.21%的Hit@3、95.79%的宏F1、94.47%的联合@3，平均分95.13%。对应提交在官方榜单排名第三，同时达到最高宏F1 93.05%，联合@3为70.16%，平均分81.61%。
原文摘要 · Abstract (English)
Scientific claim verification over a cited paper requires predicting the claim--paper relation and identifying the paragraphs that justify that prediction. This setting poses two linked challenges: within-paper distractors often resemble genuine evidence, while a classifier trained on gold evidence must operate on retrieved evidence at inference. We present HNR-DAC, a two-stage framework that trains each stage on the cases it will actually encounter. Hard-Negative Reranking (HNR) quantifies evidence confusability using a base reranker's scores on non-gold paragraphs and contrasts gold evidence against the most confusable candidates. Distribution-Aligned Classification (DAC) trains on the Top-1 paragraph produced by the same frozen HNR used to construct inference inputs, while HNR's Top-3 paragraph identifiers provide the evidence output. On the NLPCC 2026 Task 10 Track 2, the final configuration obtains 97.21% Hit@3, 95.79% Macro-F1, 94.47% Joint@3, and an average score of 95.13%. The corresponding submission ranks third on the official Track 2 leaderboard while achieving the highest overall Macro-F1 of 93.05%, alongside 70.16% Joint@3 and an average score of 81.61%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。