Multimodal vs. Text-Only Dense Retrieval Models Under Spelling Errors

Abstract

Abstract: This report synthesises findings from 4 peer-reviewed papers addressing the following research question: How do recent multimodal dense retrieval models (e.g., M3-Rec) perform in misspelling robustness tasks compared to text-only models when evaluated on benchmarks like Flickr30k or XLENT with induced. Dialogue systems powered by large language models (LLMs) show strong generative abilities but often struggle with informal language, long-term coherence, and grounded responses in expert-driven conversations. This thesis presents three complementary methods to address these. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

How do recent multimodal dense retrieval models (e.g., M3-Rec) perform in misspelling robustness tasks compared to text-only models when evaluated on benchmarks like Flickr30k or XLENT with induced spelling errors?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance