mlsanityData to 7 Oct 2026

Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models

arXiv 2407.02623 ↗First posted 2 Jul 2024cs.CY cs.AI cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Recent work has demonstrated that the unequal representation of cultures and socioeconomic groups in training data leads to biased Large Multi-modal (LMM) models. To improve LMM model performance on underrepresented data, we propose and evaluate several prompting strategies using non-English, geographic, and socioeconomic attributes. We show that these geographic and socioeconomic integrated prompts favor retrieving topic appearances commonly found in data from low-income households across different countries leading to improved LMM model performance on lower-income data. Our analyses identify and highlight contexts where these strategies yield the most improvements.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 52 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

29 of 52 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2019Language Models as Knowledge Bases?cited by 1,922
  7. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  8. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  9. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  10. 2017On Fairness and Calibrationcited by 406
  11. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  12. 2022Challenges and Strategies in Cross-Cultural NLPcited by 216
17 more
  1. 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 203
  2. 2021Visually Grounded Reasoning across Languages and Culturescited by 188
  3. 2019Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practicescited by 170
  4. 2017No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing Worldcited by 152
  5. 2019Does Object Recognition Work for Everyone?cited by 149
  6. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 147
  7. 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 102
  8. 2022Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Datasetcited by 100
  9. 2021A Survey on Gender Bias in Natural Language Processingcited by 89
  10. 2023NLLB-CLIP -- train performant multilingual image retrieval model on a budgetcited by 24
  11. 2023Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Modelscited by 16
  12. 2023The Butterfly Effect in Artificial Intelligence Systems: Implications for AI Bias and Fairnesscited by 12
  13. 2023Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Modelscited by 11
  14. 2023CoPL: Contextual Prompt Learning for Vision-Language Understandingcited by 9
  15. 2023Data Augmentation via Subgroup Mixup for Improving Fairnesscited by 8
  16. 2024Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Costcited by 5
  17. 2024Incorporating Geo-Diverse Knowledge into Prompting for Increased Geographical Robustness in Object Recognitioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understandingcited by 8
  2. 2026AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLPcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Large Language Models Substantially Compress Well-Being Inequality but Largely Preserve Its Socioeconomic Structure
  2. 2026Same Chart, Different Story: Bias in Vision-Language Chart Interpretation
  3. 2026Measurement Validity in LLM Cultural Alignment
  4. 2025From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Text
  5. 2026Understanding Cultural Alignment in Multilingual LLMs via Natural Debate Statements ↗
  6. 2024A Multi-LLM Debiasing Framework
  7. 2026Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMs
  8. 2024Large Language Models are Geographically Biased