Paper Overview
Field: NLP Authors: Shaghayegh Sadeghi, Khashayar Khajavi, Rise Adhikari, et al. Published: 2026-05-28 arXiv: 2605.27710
Summary
Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high-stakes settings. The authors present DeepSciVerify, a two-stage pipeline for scientific claim–citation verification that combines abstract-level reasoning with selective escalation to passage-level evidence.
The system first verifies claims using the abstract and defers uncertain cases, retrieving and analyzing full-text passages only when necessary. This design leverages complementary behaviors across LLMs, as some models are more conservative while others are more decisive under uncertainty.
Key Results
- On the SCitance benchmark, DeepSciVerify achieves 86.7 Micro-F1, outperforming strong abstract-only baselines by +4.5 points.
- 67% of instances are resolved without full-text retrieval, improving efficiency alongside accuracy.
- The findings suggest that selective evidence escalation is an effective strategy for claim–citation verification in high-stakes LLM-generated scientific content.
Original Abstract (excerpt)
> Misalignment between claims and their cited evidence is a common failure mode in reports generated by large language models, limiting their reliability in scientific and other high-stakes settings. We present DeepSciVerify, a two-stage pipeline for scientific claim-citation verification that combines abstract-level reasoning with selective escalation to passage-level evidence... These results suggest that selective evidence escalation [improves both accuracy and efficiency].
---
*Auto-collected on 2026-05-29*