mlsanityData to 14 Oct 2026

Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration

arXiv 2509.13919 ↗First posted 17 Sep 2025cs.CVcited by 2

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 45 of its 51 references that are in the map. First posted on arXiv 17 Sep 2025.

Builds on

45 of 51 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Step15 Nov
  2. 2024Vision-Language Models Can Self-Improve Reasoning via Reflection30 Oct
  3. 2024Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks5 Oct
  4. 2024Enhancing Large Vision Language Models with Self-Training on Image Comprehension30 May
  5. 2024Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement24 May
  6. 2024Are We on the Right Way for Evaluating Large Vision-Language Models?29 Mar
  7. 2024Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset22 Feb
  8. 2023MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts3 Oct

Other references · 37

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2024Qwen2.5 Technical Reportcited by 4,942
  8. 2024GPT-4o System Cardcited by 4,588
  9. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  10. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  11. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  12. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
25 more
  1. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  2. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,479
  3. 2020DocVQA: A Dataset for VQA on Document Imagescited by 1,317
  4. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  5. 2023SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehensioncited by 940
  6. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 858
  7. 2016A Diagram Is Worth A Dozen Imagescited by 804
  8. 2023HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Modelscited by 583
  9. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 445
  10. 2023RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedbackcited by 412
  11. 2024MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmarkcited by 372
  12. 2023Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationcited by 225
  13. 2024Aligning Modalities in Vision Large Language Models via Preference Fine-tuningcited by 198
  14. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 164
  15. 2018TallyQA: Answering Complex Counting Questionscited by 153
  16. 2024Improve Vision Language Model Chain-of-thought Reasoningcited by 136
  17. 2023Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challengescited by 131
  18. 2023Silkie: Preference Distillation for Large Visual Language Modelscited by 130
  19. 2024MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scalecited by 127
  20. 2024Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizercited by 109
  21. 2023How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMscited by 108
  22. 2024Calibrated Self-Rewarding Vision Language Modelscited by 78
  23. 2024A Closer Look at the Limitations of Instruction Tuningcited by 77
  24. 2024Self-Supervised Visual Preference Alignmentcited by 31
  25. 2024EACO: Enhancing Alignment in Multimodal LLMs via Critical Observationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Rankingcited by 17
  2. 2026BIRD: Distilling Decision Boundaries into Rationales for MLLM Adaptationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs
  2. 2025Improving Alignment in LVLMs with Debiased Self-Judgment
  3. 2024Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
  4. 2025Evaluating Variance in Visual Question Answering Benchmarks
  5. 2025Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models
  6. 2024MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)
  7. 2024FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability
  8. 2024CAST: Cross-modal Alignment Similarity Test for Vision Language Models