From Global to Local: Social Bias Transfer in CLIP

• URL: http://arxiv.org/abs/2508.17750v1
• Date: Mon, 25 Aug 2025 07:44:03 GMT
• Title: From Global to Local: Social Bias Transfer in CLIP
• Authors: Ryan Ramos, Yusuke Hirota, Yuta Nakashima, Noa Garcia,
• Abstract summary: We investigate the phenomenon of bias transfer in prior literature through a comprehensive empirical analysis.<n>We examine how pre-training bias varies between global and local views of data, finding that bias measurement is highly dependent on the subset of data on which it is computed.<n>We explore why this inconsistency occurs, showing that under the current paradigm, representation spaces of different pre-trained CLIPs tend to converge when adapted for downstream tasks.
• Score: 22.508828073380112
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The recycling of contrastive language-image pre-trained (CLIP) models as backbones for a large number of downstream tasks calls for a thorough analysis of their transferability implications, especially their well-documented reproduction of social biases and human stereotypes. How do such biases, learned during pre-training, propagate to downstream applications like visual question answering or image captioning? Do they transfer at all? We investigate this phenomenon, referred to as bias transfer in prior literature, through a comprehensive empirical analysis. Firstly, we examine how pre-training bias varies between global and local views of data, finding that bias measurement is highly dependent on the subset of data on which it is computed. Secondly, we analyze correlations between biases in the pre-trained models and the downstream tasks across varying levels of pre-training bias, finding difficulty in discovering consistent trends in bias transfer. Finally, we explore why this inconsistency occurs, showing that under the current paradigm, representation spaces of different pre-trained CLIPs tend to converge when adapted for downstream tasks. We hope this work offers valuable insights into bias behavior and informs future research to promote better bias mitigation practices.

Related papers

• Bias after Prompting: Persistent Discrimination in Large Language Models [9.558263120749356]
  We find that biases can transfer through prompting and that popular prompt-based mitigation methods do not consistently prevent biases from transferring.<n>Specifically, the correlation between intrinsic biases and those after prompt adaptation remain moderate to strong across demographics and tasks.<n>We evaluate several prompt-based debiasing strategies and find that different approaches have distinct strengths, but none consistently reduce bias transfer across models, tasks or demographics.
  arXiv  Detail & Related papers  (2025-09-09T20:59:50Z)
• Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs [51.00909549291524]
  Large language models (LLMs) exhibit cognitive biases.<n>These biases vary across models and can be amplified by instruction tuning.<n>It remains unclear if these differences in biases stem from pretraining, finetuning, or even random noise.
  arXiv  Detail & Related papers  (2025-07-09T18:01:14Z)
• On the Origins of Sampling Bias: Implications on Fairness Measurement and Mitigation [0.0]
  Several sources of bias exist and it is assumed that bias resulting from machine learning is born equally by different groups.<n> Sampling bias, in particular, is inconsistently used in the literature to describe bias due to the sampling procedure.<n>We introduce clearly defined variants of sampling bias, namely, sample size bias ( SSB) and underrepresentation bias (URB)
  arXiv  Detail & Related papers  (2025-03-23T06:23:07Z)
• Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection [18.625071242029936]
  Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content.<n>This paper presents a systematic framework to investigate and compare explicit and implicit biases in LLMs.
  arXiv  Detail & Related papers  (2025-01-04T14:08:52Z)
• How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
  This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs.<n>Our findings reveal that biases present in pre-training data are amplified in model outputs.
  arXiv  Detail & Related papers  (2024-11-28T16:20:25Z)
• When does Bias Transfer in Transfer Learning? [89.22641454588278]
  Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. We demonstrate that there can exist a downside after all: bias transfer, or the tendency for biases of the source model to persist even after adapting the model to the target class.
  arXiv  Detail & Related papers  (2022-07-06T17:58:07Z)
• Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation [31.944147533327058]
  Contrastive Debiasing via Generative Bias-transformation (CDvG) We propose a novel method, Contrastive Debiasing via Generative Bias-transformation (CDvG), which works without explicit bias labels or bias-free samples. Our method demonstrates superior performance compared to prior approaches, especially when bias-free samples are scarce or absent.
  arXiv  Detail & Related papers  (2021-12-02T07:16:06Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)
• Bayesian analysis of the prevalence bias: learning and predicting from imbalanced data [10.659348599372944]
  This paper lays the theoretical and computational framework for training models, and for prediction, in the presence of prevalence bias. It offers an alternative to principled training losses and complements test-time procedures based on selecting an operating point from summary curves. It integrates seamlessly in the current paradigm of (deep) learning using backpropagation and naturally with Bayesian models.
  arXiv  Detail & Related papers  (2021-07-31T14:36:33Z)
• Learning from Failure: Training Debiased Classifier from Biased Classifier [76.52804102765931]
  We show that neural networks learn to rely on spurious correlation only when it is "easier" to learn than the desired knowledge. We propose a failure-based debiasing scheme by training a pair of neural networks simultaneously. Our method significantly improves the training of the network against various types of biases in both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2020-07-06T07:20:29Z)
• Mitigating Gender Bias Amplification in Distribution by Posterior Regularization [75.3529537096899]
  We investigate the gender bias amplification issue from the distribution perspective. We propose a bias mitigation approach based on posterior regularization. Our study sheds the light on understanding the bias amplification.
  arXiv  Detail & Related papers  (2020-05-13T11:07:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.