Fairness in Large Language Models: A Taxonomic Survey
Open accessThe DOI matches its Crossref record; 88 of the 88 references it cites were found in a registry or an index.
Abstract
Large Language Models (LLMs) have demonstrated remarkable success across various domains. However, despite their promising performance in numerous real-world applications, most of these algorithms lack fairness considerations. Consequently, they may lead to discriminatory outcomes against certain communities, particularly marginalized populations, prompting extensive study in fair LLMs. On the other hand, fairness in LLMs, in contrast to fairness in traditional machine learning, entails exclusive backgrounds, taxonomies, and fulfillment techniques. To this end, this survey presents a comprehensive overview of recent advances in the existing literature concerning fair LLMs. Specifically, a brief introduction to LLMs is provided, followed by an analysis of factors contributing to bias in LLMs. Additionally, the concept of fairness in LLMs is discussed categorically, summarizing metrics for evaluating bias in LLMs and existing algorithms for promoting fairness. Furthermore, resources for evaluating bias in LLMs, including toolkits and datasets, are summarized. Finally, existing research challenges and open questions are discussed.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390 · cited 1×
“Language models are computational models with the capacity to comprehend and generate human language [115, 93].”
BackgroundLLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208
Large Language Models Encode Clinical Knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2212.13138 · Cited by 4,083
Large language models encode clinical knowledge
Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., et al. (2023) · Nature · doi:10.1038/s41586-023-06291-2 · Cited by 4,083 · cited 1×
“Section 3 provides background information on LLMs to facilitate an understanding of fairness in LLMs explores current definitions of fairness in ML and the adaptations necessary to address linguistic in defin-34 1 SIGKDD Explorations fairness in LLMs is presented in Section 6.”
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.243 · Cited by 3,096
The Power of Scale for Parameter-Efficient Prompt Tuning
Lester, B., Al-Rfou, R., & Constant, N. (2021) · arXiv · doi:10.48550/arxiv.2104.08691 · Cited by 3,092
PaLM: Scaling Language Modeling with Pathways
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.02311 · Cited by 2,590
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 1×
“Existing fairness definitions [60, 44] at the group level aim to emphasize that algorithmic decisions neither favor nor harm certain subgroups defined by the sensitive attribute , which often derives from legal standards or topics of social sensitivity, such as gender, race, religion, age,…”
BackgroundA Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Large Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Bolukbasi, T., Chang, K.-W., Zou, J., Saligrama, V., & Kalai, A. (2016) · arXiv · doi:10.48550/arxiv.1607.06520 · Cited by 1,615 · cited 2×
“This line of efforts begins with Bolukbasi et al. [15] conducting a seminal study that revealed the racial and gender biases inherent in Word2Vec [92] and Glove [110], two widely-used embedding schemes.”
BackgroundBellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovic, A., et al. (2018) · arXiv · doi:10.48550/arxiv.1810.01943 · Cited by 1,581
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526
Scaling Instruction-Finetuned Language Models
Chung, H. W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.11416 · Cited by 1,441 · cited 1×
“This method allows the model to learn particular tasks directed by these instructions, significantly enhancing its capacity to interpret and execute a variety of NLP tasks as per the guidelines provided [28].”
MethodBias and Fairness in Large Language Models: A Survey
Gallegos, I. O., Rossi, R. A., Barrow, J., Tanjim, M. M., Kim, S., Dernoncourt, F., Yu, T., Zhang, R., & Ahmed, N. K. (2024) · Computational Linguistics · doi:10.1162/coli_a_00524 · Cited by 1,245 · cited 1×
“This phenomenon inadvertently introduces semantic bias into downstream models, impacting their performance and fairness [50, 9].”
BackgroundFairness definitions explained
Verma, S., & Rubin, J. (2018) · Proceedings of the International Workshop on Software Fairness · doi:10.1145/3194770.3194776 · Cited by 1,124
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101
Deep reinforcement learning from human preferences
Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017) · arXiv · doi:10.48550/arxiv.1706.03741 · Cited by 1,058 · cited 1×
“For this purpose, InstructGPT [104] designs an effective tuning approach that enables LLMs to follow the expected instructions, which utilizes the technique of reinforcement learning with human feedback (RLHF) [26, 104].”
MethodSuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
Wang, A., Pruksachatkun, Y., Nangia, N., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. R. (2019) · arXiv · doi:10.48550/arxiv.1905.00537 · Cited by 1,051
Annotation Artifacts in Natural Language Inference Data
Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S., & Smith, N. A. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2017 · Cited by 907
AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
Bellamy, R. K. E., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilović, A., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2942287 · Cited by 884
Bender, E. M., & Friedman, B. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00041 · Cited by 854
The Risk of Racial Bias in Hate Speech Detection
Sap, M., Card, D., Gabriel, S., Choi, Y., & Smith, N. A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1163 · Cited by 817 · cited 1×
“In instruction tuning scenarios, biases can arise from the subjective judgments of human annotators who provide labels or annotations for training data [121].”
BackgroundLaMDA: Language Models for Dialog Applications
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T., Baker, L., Du, Y., et al. (2022) · arXiv · doi:10.48550/arxiv.2201.08239 · Cited by 778
Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems
(2023) · doi:10.1145/3544548 · Cited by 735
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Gehman, S., Gururangan, S., Sap, M., Choi, Y., & Smith, N. A. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.301 · Cited by 693
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.416 · Cited by 643
StereoSet: Measuring stereotypical bias in pretrained language models
Nadeem, M., Bethke, A., & Reddy, S. (2020) · arXiv · doi:10.48550/arxiv.2004.09456 · Cited by 643
Multitask Prompted Training Enables Zero-Shot Task Generalization
Sanh, V., Webson, A., Raffel, C., Bach, S. H., Sutawika, L., Alyafeai, Z., Chaffin, A., Stiegler, A., Scao, T. L., Raja, A., et al. (2021) · arXiv · doi:10.48550/arxiv.2110.08207 · Cited by 612 · cited 1×
“Simultaneously, the datasets need to be large enough to provide sufficient training data for LLMs, and representative enough so that the models can adapt well to new and unseen texts [120].”
BackgroundBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Srivastava, A., Rastogi, A., Rao, A., Shoeb, A. A. M., Abid, A., Fisch, A., Brown, A. R., Santoro, A., Gupta, A., Garriga-Alonso, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2206.04615 · Cited by 569
Self-citationSex and gender differences and biases in artificial intelligence for biomedicine and healthcare
Cirillo, D., Catuara-Solarz, S., Morey, C., Guney, E., Subirats, L., Mellino, S., Gigante, A., Valencia, A., Rementeria, M. J., Chadha, A. S., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0288-5 · Cited by 553
Aequitas: A Bias and Fairness Audit Toolkit
Saleiro, P., Kuester, B., Hinkson, L., London, J., Stevens, A., Anisfeld, A., Rodolfa, K. T., & Ghani, R. (2018) · arXiv · doi:10.48550/arxiv.1811.05577 · Cited by 496
Persistent Anti-Muslim Bias in Large Language Models
Abid, A., Farooqi, M., & Zou, J. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462624 · Cited by 476 · cited 1×
“Consequently, they could lead to discrimination against certain populations, especially in socially sensitive applications, across various dimensions such as race [5], age [43], gender [72], nation-ality [139], occupation [71], and religion [1].”
BackgroundOn Measuring Social Biases in Sentence Encoders
May, C., Wang, A., Bordia, S., Bowman, S. R., & Rudinger, R. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1063 · Cited by 461 · cited 2×
“Contrasting with WEAT, SEAT compares sets of sentences rather than sets of words by employing WEAT on the vector representation of a sentence.”
BackgroundMethodCrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
Nangia, N., Vania, C., Bhalerao, R., & Bowman, S. R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.154 · Cited by 446
Gender Bias in Coreference Resolution
Rudinger, R., Naradowsky, J., Leonard, B., & Van Durme, B. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers) · doi:10.18653/v1/n18-2002 · Cited by 443 · cited 1×
“Probability-based metrics formalize bias by analyzing the probabilities assigned by LLMs to various options, often predicting words or sentences based on templates [11, 116] or evaluation sets [48].”
BackgroundExamining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
Kiritchenko, S., & Mohammad, S. (2018) · Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/s18-2005 · Cited by 384
Gender bias and stereotypes in Large Language Models
Kotek, H., Dockum, R., & Sun, D. (2023) · Proceedings of The ACM Collective Intelligence Conference · doi:10.1145/3582269.3615599 · Cited by 381
Large language models are few-shot clinical information extractors
Agrawal, M., Hegselmann, S., Lang, H., Kim, Y., & Sontag, D. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.130 · Cited by 358
Measuring Bias in Contextualized Word Representations
Kurita, K., Vyas, N., Pareek, A., Black, A. W., & Tsvetkov, Y. (2019) · Proceedings of the First Workshop on Gender Bias in Natural Language Processing · doi:10.18653/v1/w19-3823 · Cited by 348 · cited 1×
“LPBS adopts template sentences similar to DisCO.”
Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
De-Arteaga, M., Romanov, A., Wallach, H., Chayes, J., Borgs, C., Chouldechova, A., Geyik, S., Kenthapadi, K., & Kalai, A. T. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287572 · Cited by 337 · cited 1×
“For example, gender bias is quantified by analyzing the difference in true positive rates of gender in classification outcomes in [6].”
BackgroundBias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting
De-Arteaga, M., Romanov, A., Wallach, H., Chayes, J., Borgs, C., Chouldechova, A., Geyik, S., Kenthapadi, K., & Kalai, A. T. (2019) · arXiv · doi:10.48550/arxiv.1901.09451 · Cited by 337
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
Ravfogel, S., Elazar, Y., Gonen, H., Twiton, M., & Goldberg, Y. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.647 · Cited by 287
Should ChatGPT be biased? Challenges and risks of bias in large language models
Ferrara, E. (2023) · First Monday · doi:10.5210/fm.v28i11.13346 · Cited by 282
GLM-130B: An Open Bilingual Pre-trained Model
Zeng, A., Liu, X., Du, Z., Wang, Z., Lai, H., Ding, M., Yang, Z., Xu, Y., Zheng, W., Xia, X., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.02414 · Cited by 281
Self-citationA survey on datasets for fairness‐aware machine learning
Le Quy, T., Roy, A., Iosifidis, V., Zhang, W., & Ntoutsi, E. (2022) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1452 · Cited by 261
Self-citationTrustLLM: Trustworthiness in Large Language Models
Huang, Y., Sun, L., Wang, H., Wu, S., Zhang, Q., Li, Y., Gao, C., Huang, Y., Lyu, W., Zhang, Y., et al. (2024) · arXiv · doi:10.48550/arxiv.2401.05561 · Cited by 256
Holistic Evaluation of Language Models
Liang, P., Bommasani, R., Lee, T., Tsipras, D., Soylu, D., Yasunaga, M., Zhang, Y., Narayanan, D., Wu, Y., Kumar, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2211.09110 · Cited by 255
BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation
Dhamala, J., Sun, T., Kumar, V., Krishna, S., Pruksachatkun, Y., Chang, K.-W., & Gupta, R. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445924 · Cited by 244 · cited 1×
“…of counterfactual-based datasets evaluates bias by presenting the model with pairs of sentences containing different demographic terms and assessing their like-7 [64] and BOLD [38], both providing web-based sentence prefixes, such as: “Jaegwon Kim was a Korean-American philosopher who . . . ”.”
MethodPredictive biases in natural language processing models: A conceptual framework and overview
Shah, D. S., Schwartz, H. A., & Hovy, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.468 · Cited by 241 · cited 1×
“Additionally, a significant disparity in the training data could also lead to biased outcomes [124].”
BackgroundMind the GAP: A balanced corpus of gendered ambiguous pronouns
Webster, K., Recasens, M., Axelrod, V., & Baldridge, J. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00240 · Cited by 223
Identifying and Reducing Gender Bias in Word-Level Language Models
Bordia, S., & Bowman, S. R. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop · doi:10.18653/v1/n19-3002 · Cited by 219 · cited 1×
“One specific method is the Co-Occurrence Bias score [98], which assesses how often tokens co-occur with gendered words in a corpus of generated text.”
MethodConscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classification
d'Alessandro, B., O'Neil, C., & LaGatta, T. (2017) · Big Data · doi:10.1089/big.2016.0048 · Cited by 195 · cited 1×
“Pre-processing methods focus on adjusting the data provided for the model, which includes both training data and prompts, in order to eliminate underlying discrimination [31]. i) Data Augmentation.”
MethodMeasuring and Reducing Gendered Correlations in Pre-trained Models
Webster, K., Wang, X., Tenney, I., Beutel, A., Pitler, E., Pavlick, E., Chen, J., Chi, E., & Petrov, S. (2020) · arXiv · doi:10.48550/arxiv.2010.06032 · Cited by 195
BBQ: A hand-built bias benchmark for question answering
Parrish, A., Chen, A., Nangia, N., Padmakumar, V., Phang, J., Thompson, J., Htut, P. M., & Bowman, S. (2022) · Findings of the Association for Computational Linguistics: ACL 2022 · doi:10.18653/v1/2022.findings-acl.165 · Cited by 186
Social chemistry 101: Learning to reason about social and moral norms
Forbes, M., Hwang, J. D., Shwartz, V., Sap, M., & Choi, Y. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.48 · Cited by 169
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
Biderman, S., Schoelkopf, H., Anthony, Q., Bradley, H., O'Brien, K., Hallahan, E., Khan, M. A., Purohit, S., Prashanth, U. S., Raff, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2304.01373 · Cited by 160
Feng, S., Park, C. Y., Liu, Y., & Tsvetkov, Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.656 · Cited by 149
Improving alignment of dialogue agents via targeted human judgements
Glaese, A., McAleese, N., Trębacz, M., Aslanides, J., Firoiu, V., Ewalds, T., Rauh, M., Weidinger, L., Chadwick, M., Thacker, P., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.14375 · Cited by 134 · cited 1×
“Large language models (LLMs) have demonstrated remarkable capabilities in addressing problems across diverse domains, ranging from chatbots [52] to medical diagnoses [147] and financial advisory [123].”
BackgroundMEDITRON-70B: Scaling Medical Pretraining for Large Language Models
Chen, Z., Cano, A. H., Romanou, A., Bonnet, A., Matoba, K., Salvi, F., Pagliardini, M., Fan, S., Köpf, A., Mohtashami, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.16079 · Cited by 122
Barikeri, S., Lauscher, A., Vulić, I., & Glavaš, G. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.151 · Cited by 121
(2023) · doi:10.18653/v1/2023.emnlp-main.632 · Cited by 115
Editing Large Language Models: Problems, Methods, and Opportunities
Yao, Y., Wang, P., Tian, B., Cheng, S., Li, Z., Deng, S., Chen, H., & Zhang, N. (2023) · arXiv · doi:10.48550/arxiv.2305.13172 · Cited by 115 · cited 1×
“This approach enables efficient adjustments to model behavior within specific areas of interest while ensuring no adverse effects on other inputs [161].”
MethodHistory, development, and principles of large language models: an introductory survey
Wang, Z., Chu, Z., Doan, T. V., Ni, S., Yang, M., & Zhang, W. (2025) · AI and Ethics · doi:10.1007/s43681-024-00583-7 · Cited by 109 · cited 1×
“The evolution of language models progresses from statistical language models to neural language models, pre-trained language models, and the current state of LLMs [27].”
Background“I’m sorry to hear that”: Finding new biases in language models with a holistic descriptor dataset
Smith, E. M., Hall, M., Kambadur, M., Presani, E., & Williams, A. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.625 · Cited by 97
HONEST: Measuring Hurtful Sentence Completion in Language Models
Nozza, D., Bianchi, F., & Hovy, D. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.191 · Cited by 95
Mitchell, E., Lin, C., Bosselut, A., Finn, C., & Manning, C. D. (2021) · arXiv · doi:10.48550/arxiv.2110.11309 · Cited by 95 · cited 1×
“Model editing, as introduced by Mitchell et al. [94], offers a method for updating LLMs that avoids the computational burden associated with training entirely new models.”
MethodUnmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
Bartl, M., Nissim, M., & Gatt, A. (2020) · arXiv · doi:10.48550/arxiv.2010.14534 · Cited by 84 · cited 1×
“Probability-based metrics formalize bias by analyzing the probabilities assigned by LLMs to various options, often predicting words or sentences based on templates [11, 116] or evaluation sets [48].”
BackgroundWinoQueer: A community-in-the-loop benchmark for anti-LGBTQ+ bias in large language models
Felkner, V., Chang, H.-C. H., Jang, E., & May, J. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.507 · Cited by 74
Perturbation augmentation for fairer NLP
Qian, R., Ross, C., Fernandes, J., Smith, E. M., Kiela, D., & Williams, A. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.646 · Cited by 69
Evaluation and mitigation of cognitive biases in medical language models
Schmidgall, S., Harris, C., Essien, I., Olshvang, D., Rahman, T., Kim, J. W., Ziaei, R., Eshraghian, J., Abadir, P., & Chellappa, R. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01283-6 · Cited by 68
Delobelle, P., Tokpo, E., Calders, T., & Berendt, B. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.122 · Cited by 57
BiasAsker: Measuring the Bias in Conversational AI System
Wan, Y., Wang, W., He, P., Gu, J., Bai, H., & Lyu, M. R. (2023) · Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3611643.3616310 · Cited by 54
TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models
Huang, Y., Zhang, Q., Y, P. S., & Sun, L. (2023) · arXiv · doi:10.48550/arxiv.2306.11507 · Cited by 47
Vanmassenhove, E., Emmery, C., & Shterionov, D. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.704 · Cited by 35 · cited 1×
“…for measuring, diagnosing, and alleviating unfairness. iii) Aequitas [119] is an open-source bias audit toolkit developed to evaluate fairness and bias in machine learning models, including LLMs, with the aim of aiding data scientists and policymakers in comprehending and addressing bias in LLMs.”
BackgroundIntrinsic bias metrics do not correlate with application bias
Goldfarb-Tarrant, S., Marchant, R., Muñoz Sánchez, R., Pandya, M., & Lopez, A. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.150 · Cited by 33
CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models
Zhao, J., Fang, M., Shi, Z., Li, Y., Chen, L., & Pechenizkiy, M. (2023) · arXiv · doi:10.48550/arxiv.2305.11262 · Cited by 31
Zhou, F., Mao, Y., Yu, L., Yang, Y., & Zhong, T. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.232 · Cited by 29
Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment
Spatharioti, S. E., Rothschild, D. M., Goldstein, D. G., & Hofman, J. M. (2023) · arXiv · doi:10.48550/arxiv.2307.03744 · Cited by 26
On measuring and mitigating biased inferences of word embeddings
Dev, S., Li, T., Phillips, J. M., & Srikumar, V. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6267 · Cited by 14
On the independence of association bias and empirical fairness in language models
Cabello, L., Jørgensen, A. K., & Søgaard, A. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3594004 · Cited by 14
Incorporating subjectivity into gendered ambiguous pronoun (GAP) resolution using style transfer
Pant, K., & Dadu, T. (2022) · Proceedings of the 4th Workshop on Gender Bias in Natural Language Processing (GeBNLP) · doi:10.18653/v1/2022.gebnlp-1.28 · Cited by 3
Cited by
History, development, and principles of large language models: an introductory survey
Wang, Z., Chu, Z., Doan, T. V., Ni, S., Yang, M., & Zhang, W. (2025) · AI and Ethics · doi:10.1007/s43681-024-00583-7 · Cited by 109
“For instance, when utilized in screening resumes for programming positions, LLMs might exhibit a bias favoring male candidates, demonstrating evident gender discrimination [157–161].”
Generative AI in depth: A survey of recent advances, model variants, and real-world applications
Yazdani, S., Singh, A., Saxena, N., Wang, Z., Palikhe, A., Pan, D., Pal, U., Yang, J., & Zhang, W. (2025) · Journal of Big Data · doi:10.1186/s40537-025-01247-x · Cited by 40
“Another area is the need to reduce the risk of biased or incorrect content, because LLMs may inadvertently inherit biases from their training corpora [194].”
Self-citationClinical insights: A comprehensive review of language models in medicine
Neveditsin, N., Lingras, P., & Mago, V. (2025) · PLOS Digital Health · doi:10.1371/journal.pdig.0000800 · Cited by 37
“However, modern LLMs often lack interpretability and remain susceptible to bias [244–246], a challenge further exacerbated by the absence of well-established, widely applicable metrics to measure these properties.”
Understanding Gender Bias in AI-Generated Product Descriptions
Kelly, M., Tahaei, M., Smyth, P., & Wilcox, L. (2025) · Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3715275.3732169 · Cited by 4
Large Language Model Reasoning Failures
Song, P., Han, P., & Goodman, N. (2026) · arXiv · doi:10.48550/arxiv.2602.06176 · Cited by 3
Metadata
- Authors
- Chu, Z., Wang, Z., & Zhang, W.
- Venue
- ACM SIGKDD Explorations Newsletter
- Published
- 2024-07-24
- Volume
- 26
- Issue
- 1
- Pages
- 34-48
- ISSN
- 1931-0145 (ISSN-L)
- 1931-0153
- OpenAlex
- W4400969772
- Cited by
- 59
- References
- 88
- FWCI
- 24.35
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.