Paper Detail

Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment

Zhan-Lun Chang, Dong-Jun Han, Seyyedali Hosseinalipour, Mung Chiang, Christopher G. Brinton

arxiv Score 11.2

Published 2026-09-08 · First seen 2026-09-09

General AI

Abstract

Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers and rerankers optimize for semantic similarity rather than answer utility, creating a preference gap: documents that appear relevant may not help the generator produce a correct answer. Motivated by this, we propose a two-stage generator-in-the-loop alignment framework that closes this gap without human document-level relevance annotations. Our framework consists of two stages: in Stage 1, a VLM generates a hypothetical text passage from the image-query pair, which is used as the retrieval query for dense text search, bridging the image-to-text modality gap. In Stage 2, a cross-encoder reranker adapted with low-rank adaptation (LoRA) is fine-tuned using answer-supervised preference pairs mined from the frozen VLM: given the dataset answer label, a candidate document is labeled positive if the VLM produces the correct answer when given that document as context, and negative otherwise. This generator-guided signal is compatible with multiple alignment loss functions, including contrastive (triplet) loss, pairwise direct preference optimization (DPO), and supervised fine-tuning (SFT), and supports periodic re-mining to refresh preference pairs as the reranker improves. Experiments on VQA-X and A-OKVQA with Qwen3.5-2B and Qwen3-VL-4B-Instruct show that our proposed framework consistently outperforms rank-order, random, and REPLUG-style likelihood baselines under various alignment losses and pool size settings, suggesting that answer-level generator feedback is an effective supervision signal for preference alignment.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{chang2026bridging,
  title = {Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment},
  author = {Zhan-Lun Chang and Dong-Jun Han and Seyyedali Hosseinalipour and Mung Chiang and Christopher G. Brinton},
  year = {2026},
  abstract = {Vision-language models (VLMs) augmented with retrieval-augmented generation (RAG) benefit from access to external evidence. However, standard retrievers and rerankers optimize for semantic similarity rather than answer utility, creating a preference gap: documents that appear relevant may not help the generator produce a correct answer. Motivated by this, we propose a two-stage generator-in-the-loop alignment framework that closes this gap without human document-level relevance annotations. Our },
  url = {https://arxiv.org/abs/2609.08188},
  keywords = {cs.AI, cs.IR},
  eprint = {2609.08188},
  archiveprefix = {arXiv},
}

Metadata

{}