Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911159282565120 |
|---|---|
| author | Wu, Yuanchen Yan, Ke Ding, Shouhong Zhou, Ziyin Li, Xiaoqiang |
| author_facet | Wu, Yuanchen Yan, Ke Ding, Shouhong Zhou, Ziyin Li, Xiaoqiang |
| contents | Large Vision-Language Models (LVLMs) have manifested strong visual question answering capability. However, they still struggle with aligning the rationale and the generated answer, leading to inconsistent reasoning and incorrect responses. To this end, this paper introduces the Self-Rationale Calibration (SRC) framework to iteratively calibrate the alignment between rationales and answers. SRC begins by employing a lightweight "rationale fine-tuning" approach, which modifies the model's response format to require a rationale before deriving an answer without explicit prompts. Next, SRC searches for a diverse set of candidate responses from the fine-tuned LVLMs for each sample, followed by a proposed pairwise scoring strategy using a tailored scoring model, R-Scorer, to evaluate both rationale quality and factual consistency of candidates. Based on a confidence-weighted preference curation process, SRC decouples the alignment calibration into a preference fine-tuning manner, leading to significant improvements of LVLMs in perception, reasoning, and generalization across multiple benchmarks. Our results emphasize the rationale-oriented alignment in exploring the potential of LVLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13919 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration Wu, Yuanchen Yan, Ke Ding, Shouhong Zhou, Ziyin Li, Xiaoqiang Computer Vision and Pattern Recognition Large Vision-Language Models (LVLMs) have manifested strong visual question answering capability. However, they still struggle with aligning the rationale and the generated answer, leading to inconsistent reasoning and incorrect responses. To this end, this paper introduces the Self-Rationale Calibration (SRC) framework to iteratively calibrate the alignment between rationales and answers. SRC begins by employing a lightweight "rationale fine-tuning" approach, which modifies the model's response format to require a rationale before deriving an answer without explicit prompts. Next, SRC searches for a diverse set of candidate responses from the fine-tuned LVLMs for each sample, followed by a proposed pairwise scoring strategy using a tailored scoring model, R-Scorer, to evaluate both rationale quality and factual consistency of candidates. Based on a confidence-weighted preference curation process, SRC decouples the alignment calibration into a preference fine-tuning manner, leading to significant improvements of LVLMs in perception, reasoning, and generalization across multiple benchmarks. Our results emphasize the rationale-oriented alignment in exploring the potential of LVLMs. |
| title | Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.13919 |