CoChat
Sign Up
Cited by 1Ethics and Social Impacts of AIAI and HR TechnologiesNames, Identity, and Discrimination Research

From Personalization to Prejudice: Bias and Discrimination in Memory-Enhanced AI Agents for Recruitment

Open access
Gharat, Himanshu, Agrawal, Himanshi, Patro, Gourab K.·2026·Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining
DOI 10.1145/3773966.3779376
Open this paper in CoChat — free account

Abstract

Large Language Models (LLMs) have empowered AI agents with advanced capabilities for understanding, reasoning, and interacting across diverse tasks. The addition of memory further enhances them by enabling continuity across interactions, learning from past experiences, and improving the relevance of actions and responses over time; termed as memory-enhanced personalization. Although such personalization through memory offers clear benefits, it also introduces risks of bias. While several previous studies have highlighted bias in ML and LLMs, bias due to memory-enhanced personalized agents is largely unexplored. Using recruitment as an example use case, we simulate the behavior of a memory-enhanced personalized agent, and study whether and how bias is introduced and amplified in and across various stages of operation. Our experiments on agents using safety-trained LLMs reveal that bias is systematically introduced and reinforced through personalization, emphasizing the need for additional protective measures or agent guardrails in memory-enhanced LLM-based AI agents.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3773966.3779376

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 47

  1. Arpit Agarwal, Rad Niazadeh, and Prathamesh Patil. 2024. Misalignment, Learning, and Ranking: Harnessing Users Limited Attention. arXiv preprint arXiv:2402.14013 (2024). · arXiv
  2. 10.1145/3460231.3473895 · DOI
  3. Marianne Bertrand and Sendhil Mullainathan. 2004. Are Emily and Greg more employable than Lakisha and Jamal? A field experiment on labor market discrimination. American economic review, Vol. 94, 4 (2004), 991-1013.
  4. 10.1145/3460231.3473897 · DOI
  5. Hongru Cai, Yongqi Li, Wenjie Wang, Fengbin Zhu, Xiaoyu Shen, Wenjie Li, and Tat-Seng Chua. 2025. Large language models empowered personalized web agents. In Proceedings of the ACM on Web Conference 2025. 198-215.
  6. L Elisa Celis, Sayash Kapoor, Farnood Salehi, and Nisheeth K Vishnoi. 2018. An algorithmic framework to control bias in bandit-based personalization. arXiv preprint arXiv:1802.08674 (2018). · arXiv
  7. Guiming Chen, Shunian Chen, Ziche Liu, Feng Jiang, and Benyou Wang. 2024a. Humans or LLMs as the Judge? A Study on Judgement Bias. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 8301-8327.
  8. 10.1007/s11280-024-01276-1 · DOI · Paper page
  9. Pedro Cisneros-Velarde. 2025. Biases in Opinion Dynamics in Multi-Agent Systems of Large Language Models: A Case Study on Funding Allocation. In Findings of the Association for Computational Linguistics: NAACL 2025. 1889-1916.
  10. Erica Coppolillo, Giuseppe Manco, and Luca Maria Aiello. 2025. Unmasking Conversational Bias in AI Multiagent Systems. CoRR (2025).
  11. Anupam Datta, Matt Fredrikson, Gihyuk Ko, Piotr Mardziel, and Shayak Sen. 2017. Proxy non-discrimination in data-driven systems. arXiv preprint arXiv:1707.08120 (2017). · arXiv
  12. Amit Datta, Michael Carl Tschantz, and Anupam Datta. 2014. Automated experiments on ad privacy settings: A tale of opacity, choice, and discrimination. arXiv preprint arXiv:1408.6491 (2014). · arXiv
  13. Maria De-Arteaga, Alexey Romanov, Hanna Wallach, Jennifer Chayes, Christian Borgs, Alexandra Chouldechova, Sahin Geyik, Krishnaram Kenthapadi, and Adam Tauman Kalai. 2019. Bias in bios: A case study of semantic representation bias in a high-stakes setting. In FAccT. 120-128.
  14. Yashar Deldjoo and Tommaso Di Noia. 2025. Cfairllm: Consumer fairness evaluation in large-language model recommender system. ACM Transactions on Intelligent Systems and Technology (2025).
  15. Yijiang Dong, Tiancheng Hu, and Nigel Collier. 2024. Can LLM be a Personalized Judge?. In Findings of EMNLP 2024. 10126-10141.
  16. 10.1145/582415.582418 · DOI · Paper page
  17. Gabbrielle M Johnson. 2025. The hard proxy problem: proxies aren't intentional; they're intentional. Philosophical Studies (2025), 1-29.
  18. Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, and Aaron Roth. 2018. Meritocratic fairness for infinite and contextual bandits. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society. 158-163.
  19. Matthew Joseph, Michael Kearns, Jamie H Morgenstern, and Aaron Roth. 2016. Fairness in learning: Classic and contextual bandits. Advances in neural information processing systems, Vol. 29 (2016).
  20. Michael Kearns, Aaron Roth, and Zhiwei Steven Wu. 2017. Meritocratic fairness for cross-population selection. In International conference on machine learning. PMLR, 1828-1836.
  21. 10.1007/s10489-017-1051-8 · DOI
  22. A Klimashevskaia, D Jannach, M Elahi, and C Trattner. [n.d.]. A survey on popularity bias in recommender systems (2023). CoRR, abs/2308.01118 ([n.d.]). · arXiv
  23. Taeyoon Kwon, Dongwook Choi, Sunghwan Kim, Hyojun Kim, Seungjun Moon, Beong-woo Kwak, Kuan-Hao Huang, and Jinyoung Yeo. 2025. Embodied Agents Meet Personalization: Exploring Memory Utilization for Personalized Assistance. arXiv preprint arXiv:2505.16348 (2025). · arXiv
  24. G Roshan Lal, Sahin Cem Geyik, and Krishnaram Kenthapadi. 2020. Fairness-aware online personalization. arXiv preprint arXiv:2007.15270 (2020). · arXiv
  25. Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, et al., 2025. From generation to judgment: Opportunities and challenges of llm-as-a-judge. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2757-2791.
  26. Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024. Llms-as-judges: a comprehensive survey on llm-based evaluation methods. arXiv preprint arXiv:2412.05579 (2024). · arXiv
  27. Dena F Mujtaba and Nihar R Mahapatra. 2024. Fairness in AI-driven recruitment: Challenges, metrics, methods, and future directions. arXiv preprint arXiv:2405.19699 (2024). · arXiv
  28. Jihwan Oh, Minchan Jeong, Jongwoo Ko, and Se-Young Yun. 2025. Understanding Bias Reinforcement in LLM Agents Debate. arXiv preprint arXiv:2503.16814 (2025). · arXiv
  29. Swetasudha Panda, Ari Kobren, Michael Wick, and Qinlan Shen. 2022. Don't just clean it, proxy clean it: Mitigating bias by proxy in pre-trained models. In Findings of the Association for Computational Linguistics: EMNLP 2022. 5073-5085.
  30. 10.1145/3531146.3533238 · DOI
  31. AGENTS MEET PERSONALIZATION. [n.d.]. PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time. ([n.d.]).
  32. Manish Raghavan, Solon Barocas, Jon Kleinberg, and Karen Levy. 2020. Mitigating bias in algorithmic hiring: Evaluating claims and practices. In FAccT. 469-481.
  33. Timo Schick, Jane Dwivedi-Yu, Roberto Dess`i, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, Vol. 36 (2023), 68539-68551.
  34. Deepa Sharma, Neha Reddy, Priya Gupta, and Rohit Sharma. 2022. Enhancing Customer Experience Personalization through AI: Leveraging Collaborative Filtering, Neural Networks, and Natural Language Processing. Journal of AI ML Research, Vol. 11, 7 (2022).
  35. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, Vol. 36 (2023), 8634-8652.
  36. Hang Su, Jun Luo, Chang Liu, Xiao Yang, Yichi Zhang, Yinpeng Dong, and Jun Zhu. 2025. A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents. arXiv preprint arXiv:2506.23844 (2025). · arXiv
  37. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023b. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023). · arXiv
  38. Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, and Furu Wei. 2023a. Augmenting language models with long-term memory. NeurIPS, Vol. 36 (2023), 74530-74543.
  39. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in neural information processing systems, Vol. 33 (2020), 5776-5788.
  40. Yining Wang, Liwei Wang, Yuanzhi Li, Di He, and Tie-Yan Liu. 2013. A theoretical analysis of NDCG type ranking measures. In Conference on learning theory. PMLR, 25-54.
  41. Ze Wang, Zekun Wu, Xin Guan, Michael Thaler, Adriano S Koshiyama, Skylar Lu, Sachin Beepath, Ediz Ertekin Jr, and María Pérez-Ortiz. 2024. JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models. In EMNLP (Findings).
  42. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837.
  43. Kyra Wilson and Aylin Caliskan. 2024. Gender, race, and intersectional bias in resume screening via language model retrieval. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, Vol. 7. 1578-1590.
  44. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR).
  45. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018. Personalizing dialogue agents: I have a dog, do you have pets too? arXiv preprint arXiv:1801.07243 (2018). · arXiv
  46. Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, et al., 2025. PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time. arXiv e-prints (2025), arXiv-2506.
  47. 10.1609/aaai.v38i17.29946 · DOI · Paper page

Cited by

Sorted by citations

Authors
Gharat, H., Agrawal, H., & Patro, G. K.
Affiliations
  • Phi Labs, Quantiphi Inc., Mumbai, Maharashtra, India
  • Phi Labs, Quantiphi Inc., Bengaluru, Karnataka, India
ORCID
Venue
Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining
Publisher
ACM
Published
2026-02-21
Pages
1140-1144
DOI
10.1145/3773966.3779376
OpenAlex
W4417530723
Cited by
0
References
1
FWCI
0.00
Type
conference paper
Language
en
Open access
Licence
cc-by-nc-nd
Locations
  • ACM International Conference on Web Search and Data Mining (WSDM) (publishedVersion, cc-by-nc-nd)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Social Sciences › Business, Management and Accounting › Organizational Behavior and Human Resource Management › AI and HR Technologies
  • Social Sciences › Sociology and Political Science › Names, Identity, and Discrimination Research
Keywords
large language models, algorithmic bias, discrimination, recruitment, personalization, bias amplification, algorithmic fairness

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