BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation

• URL: http://arxiv.org/abs/2101.11718v1
• Date: Wed, 27 Jan 2021 22:07:03 GMT
• Title: BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
• Authors: Jwala Dhamala, Tony Sun, Varun Kumar, Satyapriya Krishna, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta
• Abstract summary: Bias in Open-Ended Language Generation dataset consists of 23,679 English text generation prompts. An examination of text generated from three popular language models reveals that the majority of these models exhibit a larger social bias than human-written Wikipedia text.
• Score: 42.34923623457615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in deep learning techniques have enabled machines to generate cohesive open-ended text when prompted with a sequence of words as context. While these models now empower many downstream applications from conversation bots to automatic storytelling, they have been shown to generate texts that exhibit social biases. To systematically study and benchmark social biases in open-ended language generation, we introduce the Bias in Open-Ended Language Generation Dataset (BOLD), a large-scale dataset that consists of 23,679 English text generation prompts for bias benchmarking across five domains: profession, gender, race, religion, and political ideology. We also propose new automated metrics for toxicity, psycholinguistic norms, and text gender polarity to measure social biases in open-ended text generation from multiple angles. An examination of text generated from three popular language models reveals that the majority of these models exhibit a larger social bias than human-written Wikipedia text across all domains. With these results we highlight the need to benchmark biases in open-ended language generation and caution users of language generation models on downstream tasks to be cognizant of these embedded prejudices.

Related papers

• MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Texts [0.6053347262128919]
  MultiSocial dataset contains 472,097 texts, of which about 58k are human-written. We use this benchmark to compare existing detection methods in zero-shot as well as fine-tuned form. Our results indicate that the fine-tuned detectors have no problem to be trained on social-media texts.
  arXiv  Detail & Related papers  (2024-06-18T12:26:09Z)
• Retrieval is Accurate Generation [99.24267226311157]
  We introduce a novel method that selects context-aware phrases from a collection of supporting documents. Our model achieves the best performance and the lowest latency among several retrieval-augmented baselines.
  arXiv  Detail & Related papers  (2024-02-27T14:16:19Z)
• CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models [52.25049362267279]
  We present a Chinese Bias Benchmark dataset that consists of over 100K questions jointly constructed by human experts and generative language models. The testing instances in the dataset are automatically derived from 3K+ high-quality templates manually authored with stringent quality control. Extensive experiments demonstrate the effectiveness of the dataset in detecting model bias, with all 10 publicly available Chinese large language models exhibiting strong bias in certain categories.
  arXiv  Detail & Related papers  (2023-06-28T14:14:44Z)
• Exposing Bias in Online Communities through Large-Scale Language Models [3.04585143845864]
  This work uses the flaw of bias in language models to explore the biases of six different online communities. The bias of the resulting models is evaluated by prompting the models with different demographics and comparing the sentiment and toxicity values of these generations. This work not only affirms how easily bias is absorbed from training data but also presents a scalable method to identify and compare the bias of different datasets or communities.
  arXiv  Detail & Related papers  (2023-06-04T08:09:26Z)
• A survey on text generation using generative adversarial networks [0.0]
  This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks. The usage of adversarial learning for text generation is promising as it provides alternatives to generate the so-called "natural" language.
  arXiv  Detail & Related papers  (2022-12-20T17:54:08Z)
• Challenges in Measuring Bias via Open-Ended Language Generation [1.5552869983952944]
  We analyze how specific choices of prompt sets, metrics, automatic tools and sampling strategies affect bias results. We provide recommendations for reporting biases in open-ended language generation.
  arXiv  Detail & Related papers  (2022-05-23T19:57:15Z)
• Estimating the Personality of White-Box Language Models [0.589889361990138]
  Large-scale language models, which are trained on large corpora of text, are being used in a wide range of applications everywhere. Existing research shows that these models can and do capture human biases. Many of these biases, especially those that could potentially cause harm, are being well-investigated. However, studies that infer and change human personality traits inherited by these models have been scarce or non-existent.
  arXiv  Detail & Related papers  (2022-04-25T23:53:53Z)
• A Survey on Retrieval-Augmented Text Generation [53.04991859796971]
  Retrieval-augmented text generation has remarkable advantages and has achieved state-of-the-art performance in many NLP tasks. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks.
  arXiv  Detail & Related papers  (2022-02-02T16:18:41Z)
• Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand [117.62186420147563]
  We propose a generalization of leaderboards, bidimensional leaderboards (Billboards) Unlike conventional unidimensional leaderboards that sort submitted systems by predetermined metrics, a Billboard accepts both generators and evaluation metrics as competing entries. We demonstrate that a linear ensemble of a few diverse metrics sometimes substantially outperforms existing metrics in isolation.
  arXiv  Detail & Related papers  (2021-12-08T06:34:58Z)
• GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation [83.10599735938618]
  Leaderboards have eased model development for many NLP datasets by standardizing their evaluation and delegating it to an independent external repository. This work introduces GENIE, an human evaluation leaderboard, which brings the ease of leaderboards to text generation tasks.
  arXiv  Detail & Related papers  (2021-01-17T00:40:47Z)

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.