REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910274975432704 |
|---|---|
| author | Ye, Kai Mao, Xianwei Zhou, Sheng Shao, Zirui Mo, Ye Liu, Liangliang Huang, Haikuan Li, Bin Bu, Jiajun |
| author_facet | Ye, Kai Mao, Xianwei Zhou, Sheng Shao, Zirui Mo, Ye Liu, Liangliang Huang, Haikuan Li, Bin Bu, Jiajun |
| contents | Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval. However, existing paradigms face critical limitations due to the lack of generalizable conflict detection and intra-model constraint mechanisms to handle conflicting evidence. To address these challenges, we propose the REAL (Reasoning-Pivot Alignment) framework centered on the novel concept of the Reasoning-Pivot. Distinct from reasoning steps that prioritize internal self-derivation, a reasoning-pivot serves as an atomic unit (node or edge) in the reasoning chain that emphasizes knowledge linkage, and it typically relies on external evidence to complete the reasoning. Supported by our constructed REAL-VQA dataset, our approach integrates Reasoning-Pivot Aware SFT (RPA-SFT) to train a generalizable discriminator by aligning conflicts with pivot extraction, and employs Reasoning-Pivot Guided Decoding (RPGD), an intra-model decoding strategy that leverages these pivots for targeted conflict mitigation. Extensive experiments on diverse datasets demonstrate that REAL significantly enhances discrimination accuracy and achieves superior performance, validating our pivot-driven resolution paradigm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14065 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment Ye, Kai Mao, Xianwei Zhou, Sheng Shao, Zirui Mo, Ye Liu, Liangliang Huang, Haikuan Li, Bin Bu, Jiajun Artificial Intelligence Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval. However, existing paradigms face critical limitations due to the lack of generalizable conflict detection and intra-model constraint mechanisms to handle conflicting evidence. To address these challenges, we propose the REAL (Reasoning-Pivot Alignment) framework centered on the novel concept of the Reasoning-Pivot. Distinct from reasoning steps that prioritize internal self-derivation, a reasoning-pivot serves as an atomic unit (node or edge) in the reasoning chain that emphasizes knowledge linkage, and it typically relies on external evidence to complete the reasoning. Supported by our constructed REAL-VQA dataset, our approach integrates Reasoning-Pivot Aware SFT (RPA-SFT) to train a generalizable discriminator by aligning conflicts with pivot extraction, and employs Reasoning-Pivot Guided Decoding (RPGD), an intra-model decoding strategy that leverages these pivots for targeted conflict mitigation. Extensive experiments on diverse datasets demonstrate that REAL significantly enhances discrimination accuracy and achieves superior performance, validating our pivot-driven resolution paradigm. |
| title | REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.14065 |