Maximilian Seeth
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1
Frequent co-authors
Research Timeline
2026
Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
The paper introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alignment loss.
Highlighted terms show continued research focus across papers