Datasets for Fairness in Language Models: An In-Depth Survey

• URL: http://arxiv.org/abs/2506.23411v2
• Date: Mon, 22 Sep 2025 15:51:55 GMT
• Title: Datasets for Fairness in Language Models: An In-Depth Survey
• Authors: Jiale Zhang, Zichong Wang, Avash Palikhe, Zhipeng Yin, Wenbin Zhang,
• Abstract summary: We offer a comprehensive analysis of the most widely used fairness datasets in language model research.<n>We propose a unified evaluation framework that surfaces consistent patterns of demographic disparities across benchmarks and scoring metrics.<n>Our findings highlight an urgent need for new benchmarks that capture a broader range of social contexts and fairness notions.
• Score: 13.944063655545898
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the growing reliance on fairness benchmarks to evaluate language models, the datasets that underpin these benchmarks remain critically underexamined. This survey addresses that overlooked foundation by offering a comprehensive analysis of the most widely used fairness datasets in language model research. To ground this analysis, we characterize each dataset across key dimensions, including provenance, demographic scope, annotation design, and intended use, revealing the assumptions and limitations baked into current evaluation practices. Building on this foundation, we propose a unified evaluation framework that surfaces consistent patterns of demographic disparities across benchmarks and scoring metrics. Applying this framework to sixteen popular datasets, we uncover overlooked biases that may distort conclusions about model fairness and offer guidance on selecting, combining, and interpreting these resources more effectively and responsibly. Our findings highlight an urgent need for new benchmarks that capture a broader range of social contexts and fairness notions. To support future research, we release all data, code, and results at https://github.com/vanbanTruong/Fairness-in-Large-Language-Models/tree/main/datasets, fostering transparency and reproducibility in the evaluation of language model fairness.

Related papers

• CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment [4.732046558763803]
  We introduce CALMA, a grounded, participatory methodology for eliciting context-relevant axes for evaluation and alignment.<n>Our findings demonstrate the value of evaluation practices based on open-ended and use-case-driven processes.
  arXiv  Detail & Related papers  (2025-07-11T22:33:11Z)
• PUB: Plot Understanding Benchmark and Dataset for Evaluating Large Language Models on Synthetic Visual Data Interpretation [2.1184929769291294]
  This paper presents a novel synthetic dataset designed to evaluate the proficiency of large language models in interpreting data visualizations. Our dataset is generated using controlled parameters to ensure comprehensive coverage of potential real-world scenarios. We employ multimodal text prompts with questions related to visual data in images to benchmark several state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-04T11:19:17Z)
• Do Text-to-Vis Benchmarks Test Real Use of Visualisations? [11.442971909006657]
  This paper investigates whether benchmarks reflect real-world use through an empirical study comparing benchmark datasets with code from public repositories. Our findings reveal a substantial gap, with evaluations not testing the same distribution of chart types, attributes, and actions as real-world examples. One dataset is representative, but requires extensive modification to become a practical end-to-end benchmark. This shows that new benchmarks are needed to support the development of systems that truly address users' visualisation needs.
  arXiv  Detail & Related papers  (2024-07-29T06:13:28Z)
• Data-Centric AI in the Age of Large Language Models [51.20451986068925]
  This position paper proposes a data-centric viewpoint of AI research, focusing on large language models (LLMs) We make the key observation that data is instrumental in the developmental (e.g., pretraining and fine-tuning) and inferential stages (e.g., in-context learning) of LLMs. We identify four specific scenarios centered around data, covering data-centric benchmarks and data curation, data attribution, knowledge transfer, and inference contextualization.
  arXiv  Detail & Related papers  (2024-06-20T16:34:07Z)
• Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions [75.45274978665684]
  Vision-Language Understanding (VLU) benchmarks contain samples where answers rely on assumptions unsupported by the provided context.<n>We collect contextual data for each sample whenever available and train a context selection module to facilitate evidence-based model predictions.<n>We develop a general-purpose Context-AwaRe Abstention detector to identify samples lacking sufficient context and enhance model accuracy.
  arXiv  Detail & Related papers  (2024-05-18T02:21:32Z)
• The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation [5.249002650134171]
  Large Language Models (LLMs) have emerged as powerful support tools across various natural language tasks and a range of application domains.<n>This paper provides a comparative overview of twelve studies investigating the potential of LLMs in labelling data.<n>While the models demonstrate promising cost and time-saving benefits, there exist considerable limitations, such as representativeness, bias, sensitivity to prompt variations and English language preference.
  arXiv  Detail & Related papers  (2024-05-02T14:00:22Z)
• VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models [57.43276586087863]
  Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs. Existing benchmarks are often limited in scope, focusing mainly on object hallucinations. We introduce a multi-dimensional benchmark covering objects, attributes, and relations, with challenging images selected based on associative biases.
  arXiv  Detail & Related papers  (2024-04-22T04:49:22Z)
• Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy [27.454549324141087]
  We propose a novel VQA benchmark based on well-known visual classification datasets. We also suggest using the semantic hierarchy of the label space to ask automatically generated follow-up questions about the ground-truth category. Our contributions aim to lay the foundation for more precise and meaningful assessments.
  arXiv  Detail & Related papers  (2024-02-11T18:26:18Z)
• Capture the Flag: Uncovering Data Insights with Large Language Models [90.47038584812925]
  This study explores the potential of using Large Language Models (LLMs) to automate the discovery of insights in data. We propose a new evaluation methodology based on a "capture the flag" principle, measuring the ability of such models to recognize meaningful and pertinent information (flags) in a dataset.
  arXiv  Detail & Related papers  (2023-12-21T14:20:06Z)
• All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation [16.016546693767403]
  We propose a framework that dynamically compares the model understanding of diverse demographics to generate more equitable sentences. CAFIE produces fairer text and strikes the best balance between fairness and language modeling capability.
  arXiv  Detail & Related papers  (2023-11-09T15:39:40Z)
• TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models [0.0]
  Machine learning models can perpetuate unintended biases from unfair and imbalanced datasets. We present a dataset coupled with an approach to improve text fairness in classifiers and language models. We leverage TIDAL to develop an identity annotation and augmentation tool that can be used to improve the availability of identity context.
  arXiv  Detail & Related papers  (2023-09-07T21:44:42Z)
• Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling [70.23876429382969]
  We propose a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks. Disco-Bench consists of 9 document-level testsets in the literature domain, which contain rich discourse phenomena. For linguistic analysis, we also design a diagnostic test suite that can examine whether the target models learn discourse knowledge.
  arXiv  Detail & Related papers  (2023-07-16T15:18:25Z)
• A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [53.727460222955266]
  Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video. Recent studies have found that current benchmark datasets may have obvious moment annotation biases. We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
  arXiv  Detail & Related papers  (2022-03-10T08:58:18Z)
• Perceptual Score: What Data Modalities Does Your Model Perceive? [73.75255606437808]
  We introduce the perceptual score, a metric that assesses the degree to which a model relies on the different subsets of the input features. We find that recent, more accurate multi-modal models for visual question-answering tend to perceive the visual data less than their predecessors. Using the perceptual score also helps to analyze model biases by decomposing the score into data subset contributions.
  arXiv  Detail & Related papers  (2021-10-27T12:19:56Z)
• Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark [54.782397511033345]
  Crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts. We present a new unified cross-datasets benchmark with 14 NLI datasets and re-evaluate 9 widely-used neural network-based NLI models. Our proposed evaluation scheme and experimental baselines could provide a basis to inspire future reliable NLI research.
  arXiv  Detail & Related papers  (2020-10-15T11:50:12Z)
• Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations [67.4375210552593]
  We design experiments to understand an important but often ignored problem in visually grounded language generation. Given that humans have different utilities and visual attention, how will the sample variance in multi-reference datasets affect the models' performance? We show that it is of paramount importance to report variance in experiments; that human-generated references could vary drastically in different datasets/tasks, revealing the nature of each task.
  arXiv  Detail & Related papers  (2020-10-07T20:45:14Z)
• Beyond Leaderboards: A survey of methods for revealing weaknesses in Natural Language Inference data and models [6.998536937701312]
  Recent years have seen a growing number of publications that analyse Natural Language Inference (NLI) datasets for superficial cues. This structured survey provides an overview of the evolving research area by categorising reported weaknesses in models and datasets.
  arXiv  Detail & Related papers  (2020-05-29T17:55:57Z)

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.