HNR-DAC: Hard-Negative Reranking and Distribution-Aligned Classification for Scientific Claim Verification

2026-08-07

AI Summary

This work addresses the challenges in scientific claim verification posed by highly similar non-evidence paragraphs and distributional shifts between training and inference evidence distributions. To tackle these issues, the authors propose HNR-DAC, a two-stage framework that first employs a Hard-Negative Reranking mechanism to contrast the most confusable non-evidence passages against genuine evidence, followed by Distribution-Aligned Classification, which trains a classifier on reranked results aligned with the inference-time evidence distribution. By innovatively integrating hard-negative reranking with distribution alignment, the approach significantly enhances joint performance in evidence retrieval and claim verification. On NLPCC 2026 Task 10 Track 2, the model achieves a leading average score of 95.13% (Hit@3: 97.21%, Macro-F1: 95.79%, Joint@3: 94.47%), with an official test Macro-F1 of 93.05%, ranking third overall.

Abstract

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%.

Problem

• scientific claim verification
• evidence retrieval
• within-paper distractors
• retrieved evidence
• claim-paper relation

Innovation

• Hard-Negative Reranking
• Distribution-Aligned Classification
• Scientific Claim Verification
• Evidence Retrieval
• Two-stage Framework