DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915749836095488 |
|---|---|
| author | Chen, Haotian Long, Qingqing Pu, Siyu Luo, Xiao Ju, Wei Xiao, Meng Zhou, Yuanchun Zhao, Jianghua Wang, Xuezhi |
| author_facet | Chen, Haotian Long, Qingqing Pu, Siyu Luo, Xiao Ju, Wei Xiao, Meng Zhou, Yuanchun Zhao, Jianghua Wang, Xuezhi |
| contents | With the rapid growth of scientific literature, scientific question answering (SciQA) has become increasingly critical for exploring and utilizing scientific knowledge. Retrieval-Augmented Generation (RAG) enhances LLMs by incorporating knowledge from external sources, thereby providing credible evidence for scientific question answering. But existing retrieval and reranking methods remain vulnerable to passages that are semantically similar but logically irrelevant, often reducing factual reliability and amplifying hallucinations.To address this challenge, we propose a Deep Evidence Reranking Agent (DeepEra) that integrates step-by-step reasoning, enabling more precise evaluation of candidate passages beyond surface-level semantics. To support systematic evaluation, we construct SciRAG-SSLI (Scientific RAG - Semantically Similar but Logically Irrelevant), a large-scale dataset comprising about 300K SciQA instances across 10 subjects, constructed from 10M scientific corpus. The dataset combines naturally retrieved contexts with systematically generated distractors to test logical robustness and factual grounding. Comprehensive evaluations confirm that our approach achieves superior retrieval performance compared to leading rerankers. To our knowledge, this work is the first to comprehensively study and empirically validate innegligible SSLI issues in two-stage RAG frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16478 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering Chen, Haotian Long, Qingqing Pu, Siyu Luo, Xiao Ju, Wei Xiao, Meng Zhou, Yuanchun Zhao, Jianghua Wang, Xuezhi Computation and Language Artificial Intelligence With the rapid growth of scientific literature, scientific question answering (SciQA) has become increasingly critical for exploring and utilizing scientific knowledge. Retrieval-Augmented Generation (RAG) enhances LLMs by incorporating knowledge from external sources, thereby providing credible evidence for scientific question answering. But existing retrieval and reranking methods remain vulnerable to passages that are semantically similar but logically irrelevant, often reducing factual reliability and amplifying hallucinations.To address this challenge, we propose a Deep Evidence Reranking Agent (DeepEra) that integrates step-by-step reasoning, enabling more precise evaluation of candidate passages beyond surface-level semantics. To support systematic evaluation, we construct SciRAG-SSLI (Scientific RAG - Semantically Similar but Logically Irrelevant), a large-scale dataset comprising about 300K SciQA instances across 10 subjects, constructed from 10M scientific corpus. The dataset combines naturally retrieved contexts with systematically generated distractors to test logical robustness and factual grounding. Comprehensive evaluations confirm that our approach achieves superior retrieval performance compared to leading rerankers. To our knowledge, this work is the first to comprehensively study and empirically validate innegligible SSLI issues in two-stage RAG frameworks. |
| title | DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2601.16478 |