pith. sign in

arxiv: 2606.28340 · v1 · pith:RVQAUOUInew · submitted 2026-05-31 · 💻 cs.IR

Rethinking Fairness in LLM-Based Recommender Systems: A Survey

Song-Duo Ma , Chu-Yun Chen , Bang-An Li , Pin-Yu Chen , Shau-Yung Hsu , Yun-Nung Chen This is my paper

Pith reviewed 2026-06-30 11:17 UTC · model grok-4.3

classification 💻 cs.IR
keywords fairnesslarge language modelsrecommender systemsbias mechanismsevaluationmitigationtrustworthy AIsurvey
0
0 comments X

The pith

LLM-based recommender systems create new fairness problems from pretrained knowledge, prompts, generated explanations, and feedback loops that existing approaches do not yet address systematically.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper surveys how large language models reshape recommender systems into semantic and generative pipelines while introducing biases at multiple stages. It organizes the literature along two axes—bias mechanisms such as pretrained knowledge and decoding strategies, and fairness targets such as individual or group equity—to map current studies. The review also covers evaluation methods, mitigation techniques, and connections to related trustworthy properties including privacy and robustness. Because it is the first survey dedicated to fairness in this setting, the authors position it as a foundation for more reliable future assessments.

Core claim

Existing work on fairness in LLM-based recommender systems can be organized through a two-dimensional taxonomy of bias mechanisms and fairness targets, accompanied by an overview of evaluation protocols and mitigation strategies, together with explicit links to explainability, privacy, robustness, and controllability.

What carries the argument

The two-dimensional view of bias mechanisms and fairness targets, which classifies studies by source of bias (pretrained knowledge, prompts, explanations, decoding, feedback) and by fairness target (individual, group, or counterfactual equity).

If this is right

  • Biases can enter at distinct points including pretrained parameters, user prompts, generated explanations, decoding choices, and closed-loop feedback.
  • Fairness evaluation must be designed to cover both the new generative mechanisms and the traditional recommendation objectives.
  • Mitigation methods should be evaluated jointly with related properties such as explainability and robustness rather than in isolation.
  • A structured taxonomy makes it possible to identify which combinations of bias mechanism and fairness target remain under-studied.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Researchers could test the taxonomy by attempting to classify every new fairness paper published after the survey cutoff date.
  • If the two axes prove insufficient, future work could add a third dimension such as the stage of the recommendation pipeline.
  • The survey's emphasis on feedback loops suggests that long-term user-model interaction studies would be a direct next step for empirical validation.

Load-bearing premise

The published literature on LLM-based recommender systems is already mature enough to support a systematic two-dimensional organization without major missing categories.

What would settle it

A set of ten or more recent papers on fairness in LLM-based recommenders whose bias sources or fairness goals fall outside the two axes defined in the survey.

Figures

Figures reproduced from arXiv: 2606.28340 by Bang-An Li, Chu-Yun Chen, Pin-Yu Chen, Shau-Yung Hsu, Song-Duo Ma, Yun-Nung Chen.

Figure 1
Figure 1. Figure 1: Taxonomy of datasets used in fairness-oriented LLM4Rec research. Datasets are organized into three [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Taxonomy of fairness evaluation protocols in LLM4Rec. The protocols are categorized into four families [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
read the original abstract

Large Language Models (LLMs) are reshaping recommender systems by enabling more semantic, generative, and interactive recommendation pipelines. However, this shift also introduces new fairness challenges, as biases may arise from pretrained knowledge, prompts, generated explanations, decoding strategies, and feedback loops. This survey provides a systematic review of fairness in LLM-based recommender systems (LLM4Rec), organizing existing studies through a two-dimensional view of bias mechanisms and fairness targets, together with a structured overview of the evaluation landscape and mitigation strategies. We further connect fairness with broader trustworthy concerns, including explainability, privacy, robustness, and controllability. To the best of our knowledge, this is the first survey specifically focused on fairness in LLM4Rec, aiming to provide a structured foundation for future research on comprehensive and reliable fairness evaluation in LLM4Rec.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The manuscript is a survey on fairness in LLM-based recommender systems (LLM4Rec). It identifies new bias sources arising from pretrained knowledge, prompts, generated explanations, decoding strategies, and feedback loops; organizes the literature via a two-dimensional taxonomy of bias mechanisms and fairness targets; surveys evaluation methods and mitigation strategies; and links fairness to other trustworthy-AI dimensions including explainability, privacy, robustness, and controllability. The central positioning statement is that this is the first survey dedicated specifically to fairness in LLM4Rec.

Significance. If the literature selection proves comprehensive and the two-dimensional taxonomy proves stable, the survey would supply a useful organizing lens and evaluation overview for an emerging sub-area, helping future work avoid fragmented fairness assessments. The explicit linkage to broader trustworthy concerns is a constructive framing that could encourage holistic rather than isolated fairness studies.

minor comments (3)
  1. [Abstract, §1] Abstract and §1: the assertion that this is 'the first survey specifically focused on fairness in LLM4Rec' should be accompanied by a short, explicit enumeration of the closest prior surveys on fairness in recommender systems or on LLM4Rec in general, with a one-sentence statement of how each differs in scope.
  2. [§3] The two-dimensional taxonomy (bias mechanisms × fairness targets) is presented as the main organizing device; each cell should contain at least one concrete citation and a brief description of the mechanism or target so that readers can immediately map individual papers onto the grid.
  3. [§4, §5] Evaluation-landscape and mitigation sections would benefit from a summary table that cross-references the taxonomy cells with the metrics or techniques discussed, making the connection between taxonomy and practical guidance explicit.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their constructive review and recommendation of minor revision. The assessment correctly identifies the survey's core contributions: the two-dimensional taxonomy of bias mechanisms and fairness targets, the overview of evaluation and mitigation approaches, and the explicit connections to other trustworthy-AI dimensions. No major comments were listed in the report, so we provide no point-by-point rebuttals below. We will incorporate any minor suggestions that may arise during the revision process to strengthen the manuscript.

Circularity Check

0 steps flagged

No significant circularity in survey synthesis

full rationale

This is a literature survey paper with no original derivations, equations, fitted parameters, or predictive claims. The two-dimensional taxonomy is presented as an organizing lens drawn from cited external work, and the 'first survey' statement is a coverage assertion rather than a deductive result. No self-citation chains, self-definitional loops, or reductions of outputs to inputs by construction exist. The manuscript is self-contained as a synthesis against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a literature survey with no new parameters, axioms, or invented entities; it relies entirely on prior publications.

pith-pipeline@v0.9.1-grok · 5684 in / 981 out tokens · 42727 ms · 2026-06-30T11:17:14.482582+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

64 extracted references · 32 canonical work pages

  1. [1]

    2023 , isbn =

    Zhang, Jizhi and Bao, Keqin and Zhang, Yang and Wang, Wenjie and Feng, Fuli and He, Xiangnan , title =. 2023 , isbn =. doi:10.1145/3604915.3608860 , booktitle =

    work page doi:10.1145/3604915.3608860 2023

  2. [2]

    2025 , issue_date =

    Deldjoo, Yashar and Noia, Tommaso Di , title =. 2025 , issue_date =. doi:10.1145/3725853 , journal =

    work page doi:10.1145/3725853 2025

  3. [3]

    2024 , eprint=

    A Normative Framework for Benchmarking Consumer Fairness in Large Language Model Recommender System , author=. 2024 , eprint=

    2024

  4. [4]

    Malthouse , editor =

    Xinyi Li and Yongfeng Zhang and Edward C. Malthouse , editor =. A Preliminary Study of ChatGPT on News Recommendation: Personalization, Provider Fairness, and Fake News , booktitle =. 2023 , url =

    2023

  5. [5]

    2024 , isbn =

    Jiang, Meng and Bao, Keqin and Zhang, Jizhi and Wang, Wenjie and Yang, Zhengyi and Feng, Fuli and He, Xiangnan , title =. 2024 , isbn =. doi:10.1145/3589334.3648158 , booktitle =

    work page doi:10.1145/3589334.3648158 2024

  6. [6]

    2024 , isbn =

    Tommasel, Antonela , title =. 2024 , isbn =. doi:10.1145/3640457.3688182 , booktitle =

    work page doi:10.1145/3640457.3688182 2024

  7. [7]

    UP 5: Unbiased Foundation Model for Fairness-aware Recommendation

    Hua, Wenyue and Ge, Yingqiang and Xu, Shuyuan and Ji, Jianchao and Li, Zelong and Zhang, Yongfeng. UP 5: Unbiased Foundation Model for Fairness-aware Recommendation. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024. doi:10.18653/v1/2024.eacl-long.114

    work page doi:10.18653/v1/2024.eacl-long.114 2024

  8. [8]

    2025 , eprint=

    FairEval: Evaluating Fairness in LLM-Based Recommendations with Personality Awareness , author=. 2025 , eprint=

    2025

  9. [9]

    Proceedings of the 42nd International Conference on Machine Learning , volume =

    Fayyazi, Arya and Kamal, Mehdi and Pedram, Massoud , title =. Proceedings of the 42nd International Conference on Machine Learning , volume =. 2025 , publisher =

    2025

  10. [10]

    2025 , isbn =

    Li, Hanzhe and Shen, Dazhong and Wang, Chao and Liu, Yuting and Gu, Jingjing , title =. 2025 , isbn =. doi:10.1145/3726302.3729917 , pages =

    work page doi:10.1145/3726302.3729917 2025

  11. [11]

    2025 , eprint=

    Improving Recommendation Fairness without Sensitive Attributes Using Multi-Persona LLMs , author=. 2025 , eprint=

    2025

  12. [12]

    2026 , isbn =

    Li, Jin and Gu, Huilin and Wang, Shoujin and Zhang, Qi and Yu, Shui and Wang, Chen and Xu, Xiwei and Chen, Fang , title =. 2026 , isbn =. doi:10.1145/3774904.3793052 , booktitle =

    work page doi:10.1145/3774904.3793052 2026

  13. [13]

    2025 , isbn =

    Gao, Chongming and Chen, Ruijun and Yuan, Shuai and Huang, Kexin and Yu, Yuanqing and He, Xiangnan , title =. 2025 , isbn =. doi:10.1145/3696410.3714524 , booktitle =

    work page doi:10.1145/3696410.3714524 2025

  14. [14]

    Tianshu Shen and Jiaru Li and Mohamed Reda Bouadjenek and Zheda Mai and Scott Sanner , title =. Inf. Process. Manag. , volume =. 2023 , url =. doi:10.1016/J.IPM.2022.103139 , timestamp =

    work page doi:10.1016/j.ipm.2022.103139 2023

  15. [15]

    2025 , eprint=

    Investigating and Mitigating Stereotype-aware Unfairness in LLM-based Recommendations , author=. 2025 , eprint=

    2025

  16. [16]

    2025 , isbn =

    Hu, Yuhan and Lyu, Ziyu and Bai, Lu and Cui, Lixin , title =. 2025 , isbn =. doi:10.1145/3726302.3730145 , booktitle =

    work page doi:10.1145/3726302.3730145 2025

  17. [17]

    2026 , eprint=

    Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems , author=. 2026 , eprint=

    2026

  18. [18]

    A Study of Implicit Ranking Unfairness in Large Language Models

    Xu, Chen and Wang, Wenjie and Li, Yuxin and Pang, Liang and Xu, Jun and Chua, Tat-Seng. A Study of Implicit Ranking Unfairness in Large Language Models. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024. doi:10.18653/v1/2024.findings-emnlp.467

    work page doi:10.18653/v1/2024.findings-emnlp.467 2024

  19. [19]

    2026 , eprint=

    Can Fairness Be Prompted? Prompt-Based Debiasing Strategies in High-Stakes Recommendations , author=. 2026 , eprint=

    2026

  20. [20]

    2025 , eprint=

    Revealing Potential Biases in LLM-Based Recommender Systems in the Cold Start Setting , author=. 2025 , eprint=

    2025

  21. [21]

    2026 , eprint=

    Unveiling and Mitigating Bias in Large Language Model Recommendations: A Path to Fairness , author=. 2026 , eprint=

    2026

  22. [22]

    2025 , isbn =

    Lu, Sijin and Man, Zhibo and Luo, Fangyuan and Wu, Jun , title =. 2025 , isbn =. doi:10.1145/3726302.3730181 , booktitle =

    work page doi:10.1145/3726302.3730181 2025

  23. [23]

    Bowen Xu and JinYi Yoon and Zhimin Peng and Bhanu Pratap Singh Rawat and Giovanni Seni and Longfeng Wu and Tong Zeng and Dawei Zhou and Bo Ji , year=

  24. [24]

    2026 , isbn =

    Luo, Renqiang and Zhang, Dong and Gao, Yupeng and Shi, Wen and Hou, Mingliang and Liu, Jiaying and Wang, Zhe and Yu, Shuo , title =. 2026 , isbn =. doi:10.1145/3774904.3792168 , booktitle =

    work page doi:10.1145/3774904.3792168 2026

  25. [25]

    2026 , isbn =

    Wang, Bohao and Chen, Jiawei and Liu, Feng and Zhang, Changwang and Wang, Jun and Jin, Canghong and Chen, Chun and Wang, Can , title =. 2026 , isbn =. doi:10.1145/3774904.3792607 , booktitle =

    work page doi:10.1145/3774904.3792607 2026

  26. [26]

    Journal of Electronic Commerce Research , volume =

    A Comparative Study of Fairness in AI-Enabled and LLM-Based Recommendation Systems , author =. Journal of Electronic Commerce Research , volume =. 2025 , url =

    2025

  27. [27]

    2025 , eprint=

    BiFair: A Fairness-aware Training Framework for LLM-enhanced Recommender Systems via Bi-level Optimization , author=. 2025 , eprint=

    2025

  28. [28]

    2025 , isbn =

    Li, Yunzhe and Wang, Junting and Sundaram, Hari and Liu, Zhining , title =. 2025 , isbn =. doi:10.1145/3705328.3748077 , booktitle =

    work page doi:10.1145/3705328.3748077 2025

  29. [29]

    2026 , eprint=

    Echoes in the Loop: Diagnosing Risks in LLM-Powered Recommender Systems under Feedback Loops , author=. 2026 , eprint=

    2026

  30. [30]

    Scientific Reports , year =

    Wei Liu and Baisong Liu and Jiangcheng Qin and Xueyuan Zhang and Weiming Huang and Yangyang Wang , title =. Scientific Reports , year =. doi:10.1038/s41598-025-89965-3 , url =

    work page doi:10.1038/s41598-025-89965-3

  31. [31]

    2026 , eprint=

    Lightweight Fairness for LLM-Based Recommendations via Kernelized Projection and Gated Adapters , author=. 2026 , eprint=

    2026

  32. [32]

    i A gent: LLM Agent as a Shield between User and Recommender Systems

    Xu, Wujiang and Shi, Yunxiao and Liang, Zujie and Ning, Xuying and Mei, Kai and Wang, Kun and Zhu, Xi and Xu, Min and Zhang, Yongfeng. i A gent: LLM Agent as a Shield between User and Recommender Systems. Findings of the Association for Computational Linguistics: ACL 2025. 2025. doi:10.18653/v1/2025.findings-acl.928

    work page doi:10.18653/v1/2025.findings-acl.928 2025

  33. [33]

    Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models

    Bao, Keqin and Zhang, Jizhi and Zhang, Yang and Huo, Xinyue and Chen, Chong and Feng, Fuli. Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024. doi:10.18653/v1/2024.emnlp-main.589

    work page doi:10.18653/v1/2024.emnlp-main.589 2024

  34. [34]

    2026 , eprint=

    Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism , author=. 2026 , eprint=

    2026

  35. [35]

    2025 , isbn =

    Hou, Yimin and Kou, Yue and Shen, Derong and Zhou, Xiangmin and Li, Dong and Nie, Tiezheng and Yu, Ge , title =. 2025 , isbn =. doi:10.1145/3746252.3761126 , booktitle =

    work page doi:10.1145/3746252.3761126 2025

  36. [36]

    Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LM s for Academic Recommendations

    Shailya, Krithi and Mishra, Akhilesh Kumar and Krishnan, Gokul S and Ravindran, Balaraman. Where Should I Study? Biased Language Models Decide! Evaluating Fairness in LM s for Academic Recommendations. Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association...

    work page doi:10.18653/v1/2025.findings-ijcnlp.141 2025

  37. [37]

    2025 , isbn =

    Fan, Jing and Zhu, Chen and Wu, Han and Zhuang, Fuzhen and Wang, Deqing and Zhu, Hengshu , title =. 2025 , isbn =. doi:10.1007/978-981-95-4158-4_4 , booktitle =

    work page doi:10.1007/978-981-95-4158-4_4 2025

  38. [38]

    Refining Bias and Reward in

    Yi Zhang and Ruihong Qiu and Jiajun Liu and Guansong Pang and Sen Wang , year=. Refining Bias and Reward in

  39. [39]

    2026 , eprint=

    Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences) , author=. 2026 , eprint=

    2026

  40. [40]

    2026 , eprint=

    Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curation , author=. 2026 , eprint=

    2026

  41. [41]

    2026 , eprint=

    De-conflating Preference and Qualification: Constrained Dual-Perspective Reasoning for Job Recommendation with Large Language Models , author=. 2026 , eprint=

    2026

  42. [42]

    Proceedings of KDD 2025 Workshop on Online and Adaptive Recommender Systems (OARS '25) , year=

    Algorithmic Harms Associated with Generative Model-Augmented Recommendation Systems , author=. Proceedings of KDD 2025 Workshop on Online and Adaptive Recommender Systems (OARS '25) , year=

    2025

  43. [43]

    Proceedings of the 18th ACM Web Science Conference (WebSci '26) , year=

    Self-Promotion in LLM Recommendations , author=. Proceedings of the 18th ACM Web Science Conference (WebSci '26) , year=

  44. [44]

    2025 , issue_date =

    Zhang, Guixian and Yuan, Guan and Cheng, Debo and Liu, Lin and Li, Jiuyong and Zhang, Shichao , title =. 2025 , issue_date =. doi:10.1145/3736404 , journal =

    work page doi:10.1145/3736404 2025

  45. [45]

    2025 , issue_date =

    Deldjoo, Yashar , title =. 2025 , issue_date =. doi:10.1145/3690655 , journal =

    work page doi:10.1145/3690655 2025

  46. [46]

    2026 , url=

    Leveraging Holistic Explanations to Mitigate Popularity Bias for Recommender Systems , author=. 2026 , url=

    2026

  47. [47]

    2025 , eprint=

    LLM as Explainable Re-Ranker for Recommendation System , author=. 2025 , eprint=

    2025

  48. [48]

    2025 , isbn =

    Hasami, Arjan and Mansoury, Masoud , title =. 2025 , isbn =. doi:10.1145/3705328.3759330 , booktitle =

    work page doi:10.1145/3705328.3759330 2025

  49. [49]

    2025 , eprint=

    LLM4Rec: Large Language Models for Multimodal Generative Recommendation with Causal Debiasing , author=. 2025 , eprint=

    2025

  50. [50]

    Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness , booktitle =

    Ulysse Maes and Lien Michiels and Annelien Smets , editor =. Mitigating Misleadingness in LLM-Generated Natural Language Explanations for Recommender Systems: Ensuring Broad Truthfulness Through Factuality and Faithfulness , booktitle =. 2025 , url =

    2025

  51. [51]

    Reading Between the Prompts: How Stereotypes Shape LLM ' s Implicit Personalization

    Neplenbroek, Vera and Bisazza, Arianna and Fern \'a ndez, Raquel. Reading Between the Prompts: How Stereotypes Shape LLM ' s Implicit Personalization. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025. doi:10.18653/v1/2025.emnlp-main.1029

    work page doi:10.18653/v1/2025.emnlp-main.1029 2025

  52. [52]

    The Twelfth International Conference on Learning Representations , year=

    Beyond Memorization: Violating Privacy via Inference with Large Language Models , author=. The Twelfth International Conference on Learning Representations , year=

  53. [53]

    International Research Journal of Engineering and Technology (IRJET) , volume=

    Privacy-Preserving Large Language Model-Based Recommendation Systems: Challenges, Techniques, and Opportunities , author=. International Research Journal of Engineering and Technology (IRJET) , volume=. 2025 , url=

    2025

  54. [54]

    2025 , eprint=

    Privacy-Utility-Bias Trade-offs for Privacy-Preserving Recommender Systems , author=. 2025 , eprint=

    2025

  55. [55]

    ACM Transactions on Information Systems , volume =

    Jianghao Lin and Xinyi Dai and Yunjia Xi and Weiwen Liu and Bo Chen and Hao Zhang and Yong Liu and Chuhan Wu and Xiangyang Li and Chenxu Zhu and Huifeng Guo and Yong Yu and Ruiming Tang and Weinan Zhang , title =. ACM Transactions on Information Systems , volume =. 2025 , month =. doi:10.1145/3678004 , publisher =

    work page doi:10.1145/3678004 2025

  56. [56]

    2024 , eprint =

    Qi Wang and Jindong Li and Shiqi Wang and Qianli Xing and Runliang Niu and He Kong and Rui Li and Guodong Long and Yi Chang and Chengqi Zhang , title =. 2024 , eprint =

    2024

  57. [57]

    2024 , isbn =

    Ren, Xubin and Wei, Wei and Xia, Lianghao and Su, Lixin and Cheng, Suqi and Wang, Junfeng and Yin, Dawei and Huang, Chao , title =. 2024 , isbn =. doi:10.1145/3589334.3645458 , booktitle =

    work page doi:10.1145/3589334.3645458 2024

  58. [58]

    2024 , isbn =

    Wei, Wei and Ren, Xubin and Tang, Jiabin and Wang, Qinyong and Su, Lixin and Cheng, Suqi and Wang, Junfeng and Yin, Dawei and Huang, Chao , title =. 2024 , isbn =. doi:10.1145/3616855.3635853 , pages =

    work page doi:10.1145/3616855.3635853 2024

  59. [59]

    2022 , isbn =

    Geng, Shijie and Liu, Shuchang and Fu, Zuohui and Ge, Yingqiang and Zhang, Yongfeng , title =. 2022 , isbn =. doi:10.1145/3523227.3546767 , booktitle =

    work page doi:10.1145/3523227.3546767 2022

  60. [60]

    2022 , eprint=

    M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems , author=. 2022 , eprint=

    2022

  61. [61]

    XR ec: Large Language Models for Explainable Recommendation

    Ma, Qiyao and Ren, Xubin and Huang, Chao. XR ec: Large Language Models for Explainable Recommendation. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024. doi:10.18653/v1/2024.findings-emnlp.22

    work page doi:10.18653/v1/2024.findings-emnlp.22 2024

  62. [62]

    2024 , isbn =

    Lubos, Sebastian and Tran, Thi Ngoc Trang and Felfernig, Alexander and Polat Erdeniz, Seda and Le, Viet-Man , title =. 2024 , isbn =. doi:10.1145/3631700.3665185 , booktitle =

    work page doi:10.1145/3631700.3665185 2024

  63. [63]

    2024 , isbn =

    Hou, Yupeng and Zhang, Junjie and Lin, Zihan and Lu, Hongyu and Xie, Ruobing and McAuley, Julian and Zhao, Wayne Xin , title =. 2024 , isbn =. doi:10.1007/978-3-031-56060-6_24 , booktitle =

    work page doi:10.1007/978-3-031-56060-6_24 2024

  64. [64]

    Enhancing Reranking for Recommendation with LLM s through User Preference Retrieval

    Zhang, Haobo and Zhu, Qiannan and Dou, Zhicheng. Enhancing Reranking for Recommendation with LLM s through User Preference Retrieval. Proceedings of the 31st International Conference on Computational Linguistics. 2025

    2025