CoChat
Sign Up
Cited by 3Information Retrieval and Search BehaviorEthics and Social Impacts of AIMisinformation and Its Impacts

Answer Bubbles: Information Exposure in AI-Mediated Search

Open access
Huang, Michelle, Goyal, Agam, Saha, Koustuv, Chandrasekharan, Eshwar·2026·Findings of the Association for Computational Linguistics: EMNLP 2026
DOI 10.18653/2026.findings-emnlp.8
Open this paper in CoChat — free accountOpen PDF

Abstract

Generative search systems are increasingly replacing link-based retrieval with AI-generated summaries, yet little is known about how these systems differ in sources, language, and fidelity to cited material.We examine responses to 11,000 real search queries across five systemsvanilla GPT, Search GPT, Perplexity Search with Grok, Google AI Overviews, and traditional Google Search-at three levels: source diversity, linguistic characterization of the generated summary, and source-summary fidelity.We find that generative search systems exhibit significant source-selection biases in their citations, favoring certain sources over others.Incorporating search also selectively attenuates epistemic markers, reducing hedging by up to 60% while preserving confidence language in the AI-generated summaries.At the same time, AI summaries further compound the citation biases: Wikipedia and longer sources are disproportionately overrepresented, whereas cited social media content and negatively framed sources are substantially underrepresented.Our findings highlight the potential for answer bubbles, in which identical queries yield structurally different information realities across systems, with implications for user trust, source visibility, and the transparency of AI-mediated information access. 1

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 · 10.18653/2026.findings-emnlp.8

Cites

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

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

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

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

The citation lists haven’t been fetched yet

Cited by 3

Research works printed but not linked: 40

  1. Nikolay Babakov, David Dale, Ilya Gusev, Irina Kro- tova, and Alexander Panchenko. 2023. Don't lose the message while paraphrasing: A study on con- tent preserving style transfer. In Natural Language Processing and Information Systems, pages 47-61, Cham. Springer Nature Switzerland.
  2. Adrien Barbaresi. 2021. Trafilatura: A web scraping library and command-line tool for text discovery and extraction. In Proceedings of the 59th Annual Meet- ing of the Association for Computational Linguistics and the 11th International Joint Conference on Nat- ural Language Processing: System Demonstrations, pages 122-131, Online. Association for Computa- tional Linguistics. · DOI · Paper page
  3. Yoav Benjamini and Yosef Hochberg. 1995. Control- ling the false discovery rate: a practical and pow- erful approach to multiple testing. Journal of the Royal statistical society: series B (Methodological), 57(1):289-300.
  4. Zana Buçinca, Maja Barbara Malaya, and Krzysztof Z Gajos. 2021. To trust or to think: cognitive forc- ing functions can reduce overreliance on ai in ai- assisted decision-making. Proceedings of the ACM on Human-computer Interaction, 5(CSCW1):1-21.
  5. Chun Wei Choo. 2023. Climate change information seeking. Journal of the Association for Information Science and Technology, 74(9):1086-1099.
  6. João Coelho, Bruno Martins, Joao Magalhaes, Jamie Callan, and Chenyan Xiong. 2024. Dwell in the beginning: How language models embed long docu- ments for dense retrieval. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 370-377, Bangkok, Thailand. Association for Computational Linguistics. · DOI
  7. Sunhao Dai, Chen Xu, Shicheng Xu, Liang Pang, Zhen- hua Dong, and Jun Xu. 2024a. Bias and unfairness in information retrieval systems: New challenges in the llm era. In Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining, pages 6437-6447.
  8. Sunhao Dai, Yuqi Zhou, Liang Pang, Weihao Liu, Xi- aolin Hu, Yong Liu, Xiao Zhang, Gang Wang, and Jun Xu. 2024b. Neural retrievers are biased towards llm-generated content. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 526-537.
  9. Mohsen Fayyaz, Ali Modarressi, Hinrich Schuetze, and Nanyun Peng. 2025. Collapse of dense retrievers: Short, early, and literal biases outranking factual evi- dence. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Vol- ume 1: Long Papers), pages 9136-9152, Vienna, Austria. Association for Computational Linguistics. · DOI
  10. Yi Feng, Chen Huang, Zhibo Man, Ryner Tan, Long P. Hoang, Shaoyang Xu, and Wenxuan Zhang. 2026. Moltnet: Understanding social behavior of AI agents in the agent-native moltbook. In Third Conference on Language Modeling.
  11. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, Haofen Wang, and 1 others. 2023. Retrieval- augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2(1):32. · arXiv
  12. Drishti Goel, Agam Goyal, Veda Duddu, Olivia Pal, Jeongah Lee, Qiuyue Joy Zhong, Violeta J Rodriguez, Daniel S Brown, Dong Whi Yoo, Ravi Karkar, and 1 others. 2026. Inform, coach, relate, listen: Au- diting llm caregiving support roles. arXiv preprint arXiv:2605.29473. · arXiv
  13. Agam Goyal, Charlotte Lambert, and Eshwar Chan- drasekharan. 2026a. The language of approval: Iden- tifying the drivers of positive feedback online. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems, pages 1-23.
  14. Agam Goyal, Koyel Mukherjee, Apoorv Saxena, Anirudh Phukan, Eshwar Chandrasekharan, and Hari Sundaram. 2026b. Masking or mitigating? decon- structing the impact of query rewriting on retriever biases in RAG. In Findings of the Association for Computational Linguistics: ACL 2026, pages 8517- 8530, San Diego, California, United States. Associa- tion for Computational Linguistics. · DOI
  15. Agam Goyal, Olivia Pal, Hari Sundaram, Eshwar Chan- drasekharan, and Koustuv Saha. 2026c. Social simu- lacra in the wild: Ai agent communities on moltbook. arXiv preprint arXiv:2603.16128. · arXiv
  16. Maarten Grootendorst. 2022. Bertopic: Neural topic modeling with a class-based tf-idf procedure. arXiv preprint arXiv:2203.05794. · arXiv
  17. Desheng Hu, Joachim Baumann, Aleksandra Urman, Elsa Lichtenegger, Robin Forsberg, Aniko Hannak, and Christo Wilson. 2026. Auditing google's ai overviews and featured snippets: A case study on baby care and pregnancy. In Proceedings of the Inter- national AAAI Conference on Web and Social Media, volume 20, pages 1044-1062.
  18. Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang, Yin- wei Wei, Trung Le, Dragan Gasevic, Yuan-Fang Li, and Thanh-Toan Do. 2025. Promptdsi: Prompt-based rehearsal-free continual learning for document re- trieval. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 383-401. Springer.
  19. Yunah Jang, Megha Sundriyal, Kyomin Jung, and Meey- oung Cha. 2026. How you ask matters! adaptive rag robustness to query variations. arXiv preprint arXiv:2604.10745. · arXiv
  20. Dominik Kowald. 2024. Transparency, privacy, and fairness in recommender systems. ArXiv, abs/2406.11323. · arXiv
  21. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Red- field, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Ken- ton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natu- ral questions: A benchmark for question answering research. Transactions of the Association for Compu- tational Linguistics, 7:452-466. · DOI · Paper page
  22. Alice Li and Luanne Sinnamon. 2024. Generative ai search engines as arbiters of public knowledge: An audit of bias and authority. Proceedings of the As- sociation for Information Science and Technology, 61(1):205-217.
  23. Haoyuan Li, Yusen Zhang, Rui Zhang, and Snigdha Chaturvedi. 2025. Coverage-based fairness in multi- document summarization. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Lin- guistics: Human Language Technologies (Volume 1: Long Papers), pages 9801-9819, Albuquerque, New Mexico. Association for Computational Linguistics. · DOI
  24. Xinyi Li, Yongfeng Zhang, and Edward C Malthouse. 2024a. Large language model agent for fake news detection. arXiv preprint arXiv:2405.01593. · arXiv
  25. Yongqi Li, Xinyu Lin, Wenjie Wang, Fuli Feng, Liang Pang, Wenjie Li, Liqiang Nie, Xiangnan He, and Tat- Seng Chua. 2024b. A survey of generative search and recommendation in the era of large language models. arXiv preprint arXiv:2404.16924. · arXiv
  26. Nelson Liu, Tianyi Zhang, and Percy Liang. 2023. Eval- uating verifiability in generative search engines. In Findings of the Association for Computational Lin- guistics: EMNLP 2023, pages 7001-7025, Singapore. Association for Computational Linguistics. · DOI · Paper page
  27. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Man- dar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining ap- proach. arXiv preprint arXiv:1907.11692. · arXiv
  28. Pranav Narayanan Venkit, Philippe Laban, Yilun Zhou, Yixin Mao, and Chien-Sheng Wu. 2025. Search en- gines in the ai era: a qualitative understanding to the false promise of factual and verifiable source-cited responses in llm-based search. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, pages 1325-1340.
  29. Olivia Pal, Veda Duddu, Agam Goyal, Drishti Goel, and Koustuv Saha. 2026a. Do we know what they know we know? calibrating student trust in ai and human responses through mutual theory of mind. In Pro- ceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems, CHI EA '26, New York, NY, USA. Association for Computing Machinery. · DOI
  30. Olivia Pal, Agam Goyal, Eshwar Chandrasekharan, and Koustuv Saha. 2026b. The hidden toll of social me- dia news: Causal effects on psychosocial wellbeing. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP).
  31. Eli Pariser. 2011. The filter bubble: How the new per- sonalized web is changing what we read and how we think. Penguin.
  32. Koustuv Saha, Yoshee Jain, Chunyu Liu, Sidharth Kali- appan, and Ravi Karkar. 2026. Ai vs. humans for online support: Comparing the language of responses from llms and online communities of alzheimer's dis- ease. ACM Trans. Comput. Healthcare, 7(3). · DOI
  33. Saron Samuel, Benjamin Van Durme, and Eugene Yang. 2026. Does reasoning make search more fair? comparing fairness in reasoning and non-reasoning rerankers. In European Conference on Information Retrieval, pages 305-318. Springer.
  34. Nikhil Sharma, Q Vera Liao, and Ziang Xiao. 2024. Generative echo chamber? effect of llm-powered search systems on diverse information seeking. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, pages 1-17.
  35. Anirudh Srinivasan and Eunsol Choi. 2022. TyDiP: A dataset for politeness classification in nine typolog- ically diverse languages. In Findings of the Associ- ation for Computational Linguistics: EMNLP 2022, pages 5723-5738, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. · DOI
  36. Hao Sun, Zile Qiao, Jiayan Guo, Xuanbo Fan, Yingyan Hou, Yong Jiang, Pengjun Xie, Yan Zhang, Fei Huang, and Jingren Zhou. 2025. Zerosearch: Incen- tivize the search capability of llms without searching. arXiv preprint arXiv:2505.04588. · arXiv
  37. Daniel Trielli and Nicholas Diakopoulos. 2019. Search as news curator: The role of google in shaping at- tention to news information. In Proceedings of the 2019 CHI Conference on human factors in computing systems, pages 1-15.
  38. Elisabeth Vogl, Reinhard Pekrun, Kou Murayama, and Kristina Loderer. 2020. Surprised-curious- confused: Epistemic emotions and knowledge ex- ploration. Emotion, 20(4):625.
  39. Tu Vu, Mohit Iyyer, Xuezhi Wang, Noah Constant, Jerry Wei, Jason Wei, Chris Tar, Yun-Hsuan Sung, Denny Zhou, Quoc Le, and Thang Luong. 2024. Fresh- LLMs: Refreshing large language models with search engine augmentation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 13697-13720, Bangkok, Thailand. Association for Computational Linguistics. · DOI · Paper page
  40. Haofei Xu, Umar Iqbal, and Jacob M Montgomery. 2026. Measuring google ai overviews: Activation, source quality, claim fidelity, and publisher impact. arXiv preprint arXiv:2605.14021. · arXiv

Authors
Huang, M., Goyal, A., Saha, K., & Chandrasekharan, E.
Affiliations
University of Illinois Urbana-Champaign (US)
ORCID
Venue
Findings of the Association for Computational Linguistics: EMNLP 2026
Publisher
Association for Computational Linguistics
Published
2026
Pages
147-162
DOI
10.18653/2026.findings-emnlp.8
OpenAlex
W7138934733
Cited by
3
References
0
Citations by year
2026: 3
FWCI
17.44
Type
conference paper
Language
en
Open access
Locations
  • Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • arXiv (Cornell University) (cc-by)
Funders
  • National Science Foundation (2137603, 2138259, 2138296, 2138307, 2138286)
  • Office of Advanced Cyberinfrastructure (#2138286, #2138296, 2138259, #2138307, 2137603)
Topics
  • Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
  • Social Sciences › Safety Research › Ethics and Social Impacts of AI
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
Keywords
generative search, citation bias, source diversity, epistemic markers, hedging, AI-generated summaries, information exposure

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