betaFeedback

Reading v1View latest version

WorksComputer Science

Token-Level Advertising

Abstract

Generative AI is transforming how people access information, challenging traditional advertising mechanisms built around predefined slots. Towards generation-native advertising, we propose the Latent Advertiser Mixture Auction (LAMA), a token-level advertising mechanism that embeds advertiser influence directly into the generation process. Advertisers report local continuation values that induce advertiser-specific next-token policies, from which the platform decodes through a latent mixture while updating an allocation posterior. We show that LAMA satisfies Markov DSIC and IR, and achieves near-optimal KL-regularized welfare. We further develop a learning-based implementation that reconstructs the required reports online from learned local advantages and root values. Proof-of-concept experiments on real-world commercial-search query splits show that LAMA improves platform welfare and revenue while maintaining user-facing response quality, providing initial evidence for the feasibility of generation-native advertising.

CCS Concepts

• Theory of computation → Algorithmic mechanism design;

• Information systems → Online advertising.

Introduction

“The medium is the message.”

— Marshall McLuhan, Understanding Media (1964)

The medium through which people access online information is undergoing a fundamental transformation. For decades, internet interfaces have largely organized information by retrieving, ranking, and presenting content that already exists. Search engines return ranked results; recommendation systems select items from a collection. Generative AI introduces a different mode of information access. Rather than simply choosing what to present, AI-native interfaces synthesize responses dynamically around user intent, with the content itself taking shape as the interaction unfolds. The medium is no longer merely organizing information; it is generating it.

Advertising has historically been built around the structure of the medium in which it appears. In traditional internet interfaces, this has led to a simple but powerful abstraction: the slot. Whether it is a sponsored-search position, a reserved display placement, or a promoted position in a recommendation feed, the commercial opportunity can typically be defined in advance and then assigned to advertisers. But this abstraction becomes less natural when the surrounding content is itself generated. As shown in Figure 1, a product may become relevant only as an answer develops in a particular direction, and only a generation choice can make a later brand mention either natural or jarring. In such settings, generation does more than fill an advertising opportunity—it can help create one. The advertising opportunity is no longer merely a slot inside generated content; it can be shaped by the generation process itself.

A search interface with sponsored product listings and a generated response containing integrated advertisements

Figure 1. In generation-native advertising, ad opportunities are no longer predefined slots: when they emerge, which advertisers are shown, and how they are presented jointly shape user experience and marketing effectiveness.

This shift calls for a corresponding change in mechanism design. Traditional advertising mechanisms largely separate two questions: what opportunities exist, and who should receive them? Auction theory has developed powerful tools for the latter, typically taking the former as given. This separation is natural when the advertising slot exists before the auction begins, but begins to break down when the generation trajectory itself determines whether and how an advertiser can be meaningfully incorporated. Thus, a mechanism that only allocates predefined opportunities leaves an important part of the generative medium outside the allocation process.

Recent work has begun to rethink what constitutes an advertising opportunity in generative interfaces. Rather than relying only on fixed slots, some approaches define opportunities over segments or context-dependent positions within generated text, while others first construct complete candidate responses and then select, aggregate, or insert sponsored content at the response level. These abstractions make advertising substantially more adaptive to generated context: where an ad can appear, or which sponsored response is appropriate, may now depend on the content produced by the model. Yet the mechanism typically operates on an opportunity that has already been identified—a segment, a position, or a completed response. Generation shapes the opportunity, but is not itself the allocation process.

In this paper, we take the next step and formulate a generation-native paradigm for computational advertising, in which advertising is directly embedded into the generation process. Advertisers are treated as strategic participants whose messages can influence how the response evolves, while the platform jointly determines generated content, advertising allocation, and payments. Within this broader paradigm, we study a particularly native instantiation at the token level: advertisers may influence the response at every generation step. A user query initializes a sequential process, and at each generated prefix, the platform combines advertiser messages with the reference language model and the current mechanism state to determine what token to generate next and how the advertising allocation should evolve. The goal is to incorporate advertiser incentives and platform monetization into generation while preserving the naturalness and usefulness of the generated content.

Making advertising a native part of generation introduces several technical challenges. Most importantly, incentive design becomes inherently sequential: a report submitted at one prefix can change the future generation trajectory, which in turn changes the advertiser’s subsequent opportunities and eventual payoff. Truthful behavior must therefore remain optimal not only at the beginning of generation, but also after any reachable future states. Advertiser influence must also be balanced against the reference language model so that monetization does not come at the expense of response quality. At the same time, language model inference already incurs substantial serving latency, requiring the mechanism to introduce only minimal additional overhead. Finally, a tractable mechanism should still admit a meaningful efficiency guarantee relative to an ideal welfare-maximizing benchmark.

To address these challenges, we propose the Latent Advertiser Mixture Auction (LAMA) for the fundamental single-winner setting. At each prefix, advertisers’ local reports induce advertiser-specific next-token policies, and LAMA generates next token from a latent mixture of these policies. The mixture weights evolve as a Bayesian allocation posterior as tokens are observed, linking the generation trajectory to the eventual advertising allocation. Once generation terminates, this posterior determines the final allocation, together with payments designed for the sequential setting. We show that LAMA satisfies Markov dominant-strategy incentive compatibility and individual rationality. Moreover, it achieves near-optimal KL-regularized welfare, with the optimality gap vanishing as the regularization diminishes.

We further develop a practical implementation that avoids explicitly reasoning over the full token tree or requiring advertisers to compute complex reports themselves. The platform provides reporting as a learned service: a shared advertiser-conditioned model recovers local signals along the realized generation path and anchors them with an advertiser-specific root estimate, allowing the reports required by LAMA to be reconstructed online. This design turns the theoretical sequential mechanism into a lightweight serving-time procedure that can operate over a small candidate set of advertisers with modest additional language-model computation.

We evaluate LAMA in simulation on real-world query splits with model-predicted impression values. We compare against heuristic mechanisms that allocate advertising either before or after generation, as well as a representative response-level aggregation mechanism. Across the evaluated settings, LAMA achieves the strongest platform welfare and revenue while maintaining high advertiser value and user-side response quality. These results provide an initial proof of concept for the generation-native advertising paradigm: allowing advertisers to participate directly in the token-level generation process can improve monetization while preserving high-quality generated responses.

Our contributions are summarized as follows.

(1) Generation-native advertising. We develop a token-level formulation of generation-native advertising, where advertiser participation is embedded directly into the sequential generation process and jointly shapes the response and eventual allocation.

(2) Token-level mechanism design. We propose LAMA for the fundamental single-winner setting and establish Markov DSIC and IR, together with near-optimal KL-regularized welfare, with an additive gap of at most βlog⁡∣V∣\beta\log|\mathcal{V}|.

(3) Practical implementation. We develop a learning-based implementation that reconstructs the reports required by LAMA online and supports efficient serving.

(4) Proof-of-concept evaluation. Experiments on real-world search query splits show that LAMA improves platform welfare and revenue while maintaining advertiser value and user-facing response quality.

Model

We model token-level advertising as a sequential mechanism embedded in the generation process of a language model. A user query initializes a token-level decision process. At each non-terminal prefix, advertisers may submit local reports based on the publicly observed state, and the platform uses these reports together with its privately observed history to choose the next token distribution, the advertising allocation, and payments. The central distinction from classical sponsored-search models is that the advertising opportunity is not an exogenously given slot. Instead, it is endogenously shaped by the generated trajectory itself.

Context space and reference generation. Let V\mathcal{V} be the token vocabulary and let LL be the maximum generation length.2 The context space is S:=V≤L=⋃t=0LVt\mathcal{S} := \mathcal{V}^{\le L} = \bigcup_{t=0}^{L} \mathcal{V}^{t}, where V0={∅}\mathcal{V}^{0} = \{\emptyset\}. For two contexts x1,x2∈Sx_{1},x_{2} \in\mathcal{S}, we write [x1,x2][x_{1},x_{2}] for their concatenation whenever the resulting sequence has length at most LL. A user query q∈Sq \in\mathcal{S} is drawn from a query distribution D\mathcal{D} and serves as the initial state.

The platform has an organic language-model policy πref(⋅∣s)∈Δ++(V)\pi_{\mathrm{ref}}(\cdot\mid s) \in\Delta_{++}(\mathcal{V}), s∈Ss \in\mathcal{S}, which describes the next-token distribution in the absence of advertising intervention3. We also write π0\pi_0 for πref\pi_{\mathrm{ref}}. A trajectory from query qq is τ=(s0=q,a0,s1,a1,…,sTτ)\tau=(s_0=q,a_0,s_1,a_1,\ldots,s_{T_\tau}), st+1=[st,at]s_{t+1}=[s_t,a_t]. Let EOS ∈V\in\mathcal{V} denote the end-of-sequence token. A state is terminal if it contains EOS or reaches the maximum length. We denote the terminal set by ST\mathcal{S}_T, and write L(s)⊆STL(s)\subseteq\mathcal{S}_T for the set of terminal descendants of a non-terminal state ss. For a trajectory τ\tau, its realized terminal state is denoted by ℓ(τ)=sTτ\ell(\tau)=s_{T_\tau}.

Advertisers and private types. There are n≥2n\ge2 advertisers, indexed by N=[n]={1,…,n}\mathcal{N}=[n]=\{1,\ldots,n\}. Each advertiser ii has a private terminal reward function ri:ST→R≥0r_i:\mathcal{S}_T\to\mathbb{R}_{\ge0}. The value ri(ℓ)r_i(\ell) represents advertiser ii’s value from receiving the advertising opportunity when the generated response terminates at ℓ\ell. We write r=(r1,…,rn)r=(r_1,\ldots,r_n) for the type profile and r−ir_{-i} for the profile excluding advertiser ii.

The allocation of the advertising opportunity is represented by a vector λ∈Λ⊆[0,1]n\lambda\in\Lambda\subseteq[0,1]^n, where Λ\Lambda is an exogenously given feasible allocation set. For example, Λ\Lambda may encode slot-capacity constraints or exposure constraints. This paper focuses on the fundamental single-winner setting: the advertising opportunity is endogenously shaped by the generation process, but the eventual sponsored outcome is assigned to a single advertiser. Thus, Λ=Δ(N)\Lambda=\Delta(\mathcal{N}). The realized gross value of advertiser ii on trajectory τ\tau is therefore λiri(ℓ(τ))\lambda_i r_i(\ell(\tau)).

Platform histories. To describe a mechanism that operates during generation, we introduce the history privately observed by the platform. A platform history at time tt is

ht=(s0,m0,a0,…,st−1,mt−1,at−1,st),h_t=(s_0,m_0,a_0,\ldots,s_{t-1},m_{t-1},a_{t-1},s_t),

where s0=qs_0=q, at∈Va_t\in\mathcal{V} is the token generated at time tt, and mt=(m1,t,…,mn,t)m_t=(m_{1,t},\ldots,m_{n,t}) denotes the profile of messages submitted by the advertisers at time tt. Advertisers observe only the current state sts_t, which is public, whereas the platform observes the entire history. The state evolves deterministically according to st+1=[st,at]s_{t+1}=[s_t,a_t]. Let H\mathcal{H} denote the set of non-terminal platform histories, and let s(h)s(h) be the current state at the end of history hh. A terminal platform history is denoted by hT=(s0,m0,a0,…,sT−1,mT−1,aT−1,sT)h_T=(s_0,m_0,a_0,\ldots,s_{T-1},m_{T-1},a_{T-1},s_T), where sT∈STs_T\in\mathcal{S}_T. We write τ(hT)\tau(h_T) for the token trajectory induced by the terminal history hTh_T, and ℓ(hT)=sT\ell(h_T)=s_T for its terminal state.

Sequential mechanisms. A sequential mechanism for token-level advertising is a tuple

Γ=({Mi(h)}i∈N,h∈H,x,λ,p).\Gamma=\left(\{M_i(h)\}_{i\in\mathcal{N},h\in\mathcal{H}},x,\lambda,p\right).

For each non-terminal platform history hh, Mi(h)M_i(h) is advertiser ii’s feasible message space after that history. Given h∈Hh\in\mathcal{H} and a joint message m=(m1,…,mn)∈M(h)=∏i∈NMi(h)m=(m_1,\ldots,m_n)\in M(h)=\prod_{i\in\mathcal{N}}M_i(h), the next-token rule is x(⋅∣h,m)∈Δ(V)x(\cdot\mid h,m)\in\Delta(\mathcal{V}). The instantaneous payment rule is pi(h,m,a)∈Rp_i(h,m,a)\in\mathbb{R}, which specifies advertiser ii’s payment when token aa is generated after history hh under report profile mm. The final allocation is λ(hT)∈Λ\lambda(h_T)\in\Lambda. Thus, the feasible message spaces, token-generation rule, payments, and final allocation may depend on the entire platform history4. In particular, history-dependent message spaces allow the platform to check a new report against values previously recorded in its report ledger.

The timing is as follows.

  1. The user query q∼Dq\sim\mathcal{D} initializes the process at s0=qs_0=q.

  1. At each non-terminal state sts_t, each advertiser ii submits a message mi,t∈Mi(ht)m_{i,t}\in M_i(h_t). Let mt=(m1,t,…,mn,t)m_t=(m_{1,t},\ldots,m_{n,t}).

  1. The mechanism chooses a next-token distribution x(⋅∣ht,mt)x(\cdot\mid h_t,m_t), draws at∼x(⋅∣ht,mt)a_t\sim x(\cdot\mid h_t,m_t), and charges pi(ht,mt,at)p_i(h_t,m_t,a_t) for each i∈Ni\in\mathcal{N}.

  1. The state updates deterministically as st+1=[st,at]s_{t+1}=[s_t,a_t]. If st+1∈STs_{t+1}\in\mathcal{S}_T, the process terminates and the mechanism implements the feasible allocation λ(hT)∈Λ\lambda(h_T)\in\Lambda.

Direct mechanisms are a special case as the platform can ask each advertiser to submit its entire reward function. However, such mechanisms are impractical for online generation because full reporting may be slow and may reveal private information about trajectories that are never realized. Our definition therefore emphasizes lightweight reports, and we will see that they suffice to achieve strong performance for the platform.

Strategies and induced policies. Let Θi\Theta_i denote advertiser ii’s type space. A strategy of advertiser ii maps its type and each non-terminal public state to a message: σi:Θi×(S∖ST)→⋃h∈HMi(h)\sigma_i:\Theta_i\times(\mathcal{S}\setminus\mathcal{S}_T)\to\bigcup_{h\in\mathcal{H}}M_i(h). A strategy is feasible if σi(ri,s(h))∈Mi(h)\sigma_i(r_i,s(h))\in M_i(h) at every history at which it is used. Given σ=(σ1,…,σn)\sigma=(\sigma_1,\ldots,\sigma_n) and type profile rr, the induced joint report at history hh is mσ,r(h):=(σ1(r1,s(h)),…,σn(rn,s(h)))m^{\sigma,r}(h):=(\sigma_1(r_1,s(h)),\ldots,\sigma_n(r_n,s(h))). Together with the mechanism Γ\Gamma, these reports determine the continuation token policy πσ,rΓ(a∣h):=x(a∣h,mσ,r(h)), a∈V\pi^{\Gamma}_{\sigma,r}(a\mid h):=x(a\mid h,m^{\sigma,r}(h)),\ a\in\mathcal{V}, and hence a distribution Pσ,rΓ(⋅∣h)\mathbb{P}^{\Gamma}_{\sigma,r}(\cdot\mid h) over terminal histories extending hh.

References

  1. [2]Gagan Aggarwal, Jon Feldman, S. Muthukrishnan, and Martin Pál. 2008. Sponsored Search Auctions with Markovian Users. In Internet and Network Economics, 4th International Workshop, WINE 2008, Shanghai, China, December 17-20, 2008. Proceedings (Lecture Notes in Computer Science), Christos H. Papadimitriou and Shuzhong Zhang (Eds.). Springer, 621–628. doi:10.1007/978-3-540-92185-1_68DOI
  2. [3]Nan An, Weian Li, Qi Qi, and Jiang Zhang. 2025. Merging Mechanisms for Ads and Organic Items in E-commerce Platforms. Proceedings of the AAAI Conference on Artificial Intelligence 39, 13 (April 2025), 13547–13554. doi:10.1609/aaai.v39i13.33479DOI
  3. [4]Santiago Balseiro, Kshipra Bhawalkar, Yuan Deng, Zhe Feng, Jieming Mao, Aranyak Mehta, Vahab Mirrokni, Renato Paes Leme, Di Wang, and Song Zuo. 2025. Position Auctions in AI-Generated Content. arXiv:2506.03309 [cs.GT] https://arxiv.org/abs/2506.03309
  4. [6]Carlos Carrion, Zenan Wang, Harikesh Nair, Xianghong Lou, Yulin Lei, Peiqin Gu, Xiliang Lin, Wenlong Chen, Junsheng Jin, Fanan Zhu, Changping Peng, Yongjun Bao, Zhangeng Lin, Weipeng Yan, and Jingping Shao. 2023. Blending Advertising with Organic Content in E-commerce via Virtual Bids. Proceedings of the AAAI Conference on Artificial Intelligence 37, 13 (June 2023), 15476–15484. doi:10.1609/aaai.v37i13.26835
  5. [7]Ruggiero Cavallo and Christopher A. Wilkens. 2014. GSP with General Independent Click-through-Rates. In Web and Internet Economics - 10th International Conference, WINE 2014, Beijing, China, December 14-17, 2014. Proceedings (Lecture Notes in Computer Science), Tie-Yan Liu, Qi Qi, and Yinyu Ye (Eds.). Springer, 400–416. doi:10.1007/978-3-319-13129-0_32DOI
  6. [8]Avinava Dubey, Zhe Feng, Rahul Kidambi, Aranyak Mehta, and Di Wang. 2024. Auctions with LLM Summaries. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, Barcelona, Spain, August 25-29, 2024, Ricardo Baeza-Yates and Francesco Bonchi (Eds.). ACM, 713–722. doi:10.1145/3637528.3672022
  7. [9]Paul Dütting, Vahab Mirrokni, Renato Paes Leme, Haifeng Xu, and Song Zuo. 2024. Mechanism Design for Large Language Models. In Proceedings of the ACM on Web Conference 2024, WWW 2024, Singapore, May 13-17, 2024, Tat-Seng Chua, Chong-Wah Ngo, Ravi Kumar, Hady W. Law, and Roy Ka-Wei Lee (Eds.). ACM, 144–155. doi:10.1145/3589334.3645511 Benjamin Edelman, Michael Ostrovsky, and Michael Schwarz. 2007. Internet Advertising and the Generalized Second-Price Auction: Selling Billions of Dollars Worth of Keywords. American Economic Review 97, 1 (Feb. 2007), 242–259. doi:10.1257/aer.97.1.242
  8. [11]Nicola Gatti, Marco Rocco, Paolo Serafino, and Carmine Venture. 2016. Towards Better Models of Externalities in Sponsored Search Auctions. In ECAI 2016 - 22nd European Conference on Artificial Intelligence, 29 August-2 September 2016, The Hague, The Netherlands - Including Prestigious Applications of Artificial Intelligence (PAIS 2016) (Frontiers in Artificial Intelligence and Applications), Gal A. Kaminka, Maria Fox, Paolo Bouquet, Eyke Hüllermeier, Virginia Dignum, Frank Dignum, and Frank van Harmelen (Eds.). IOS Press, 1167–1175. doi:10.3233/978-1-61499-672-9-1167
  9. [12]Nicola Gatti, Marco Rocco, Paolo Serafino, and Carmine Venture. 2018. Towards better models of externalities in sponsored search auctions. Theor. Comput. Sci. 745 (2018), 150–162. doi:10.1016/J.TCS.2018.06.011DOI
  10. [13]Artur Gruschka and Mohammad Mahdian. 2008. Externalities in online advertising. In Proceedings of the 17th International Conference on World Wide Web, WWW 2008, Beijing, China, April 21-25, 2008, Jinpeng Huai, Robin Chen, Hsiao-Wuen Hon, Yuhui Luo, Wei-Ying Ma, Andrew Tomkins, and Xiaodong Zhang (Eds.). ACM, 161–168. doi:10.1145/1367497.1367520
  11. [14]Ioannis G. Krishnamurthy and Anna R. Karlin. 2008. On the Equilibria and Efficiency of the GSP Mechanism in Keyword Auctions with Externalities. In Internet and Network Economics, 4th International Workshop, WINE 2008, Shanghai, China, December 17-20, 2008. Proceedings (Lecture Notes in Computer Science), Christos H. Papadimitriou and Shuzhong Zhang (Eds.). Springer, 629–638. doi:10.1007/978-3-540-92185-1_69
  12. [15]MohammadTaghi Hajiaghayi, Sébastien Lahaie, Keivan Rezaei, and Suho Shin. 2024. Ad Auctions for LLMs via Retrieval Augmented Generation. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.). Vol. 37. Curran Associates, Inc., 18445–18480. doi:10.52202/0789017-0585
  13. [16]Jiale Han and Xiaowu Dai. 2026. Mechanism Design for Quality-Preserving LLM Advertising. arXiv:2605.10964 [cs.GT] https://arxiv.org/abs/2605.10964
  14. [18]Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021).arxiv.org/abs/2106.09685
  15. [19]Silan Hu, Shiqi Zhang, Yimin Shi, and Xiaokui Xiao. 2026. GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing. arXiv:2509.14221 [cs.IR] https://arxiv.org/abs/2509.14221
  16. [20]Weian Li, Qi Qi, Changjun Wang, and Changyuan Wu. 2023. Optimally integrating ad auction into e-commerce platforms. Theoretical Computer Science 976 (Oct. 2023), 114141. doi:10.1016/j.tcs.2023.114141DOI
  17. [21]Iv12. 2024. esci-ms-marco-MiniLM-L-12-v2. https://huggingface.co/iv12/esci-ms-marco-MiniLM-L-12-v2. Cross-encoder fine-tuned on the Amazon ESCI dataset; based on cross-encoder/ms-marco-MiniLM-L12-v2.
  18. [23]Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems 35 (2022), 27730–27744.
  19. [24]Sebastian Schmidt, Ines Zelch, Janek Bevendorff, Benno Stein, Matthias Hagen, and Martin Potthast. 2024. Detecting Generated Native Ads in Conversational Search. In Companion Proceedings of the ACM Web Conference 2024. ACM, 722–725. doi:10.1145/3589335.3651489DOI
  20. [25]Ermis Soumaliас, Michael J. Curry, and Sven Seuken. 2024. Truthful Aggregation of LLMs with an Application to Online Advertising. CoRR abs/2405.05905 (2024), arXiv:2405.05905 doi:10.48550/ARXIV.2405.05905arxiv.org/abs/2405.05905
  21. [26]Haoran Sun, Xinrui Song, Xinyu Zhang, Zhaohua Chen, Xu Chu, Zhilin Zhang, Chuan Yu, Jian Xu, Bo Zheng, and Xiaotie Deng. 2026. LLM-Enhanced RAG for Ad Auction in Generative Chatbots. arXiv:2605.16474 [cs.IR] https://arxiv.org/abs/2605.16474
  22. [27]Hal R. Varian. 2007. Position Auctions. International journal of Industrial Organization 25, 6 (Dec. 2007), 1163–1178. doi:10.1016/j.ijindorg.2006.10.002DOI
  23. [28]Shengwei Xu, Zhaohua Chen, Xiaotie Deng, Zhiyi Huang, and Grant Schoenebeck. 2026. Ad Insertion in LLM-Generated Responses. arXiv:2601.19435 [cs.GT] https://arxiv.org/abs/2601.19435
  24. [29]An Yang, Feng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengren Huang, Chenxu Lv, et al. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025).arxiv.org/abs/2505.09388
  25. [30]Peiran Yun, Wenxin Xu, Jiayuan Liu, Yihang Zhang, Liang Zeng, Lingkai Kong, and Tonghan Wang. 2026. LLM Advertisement based on Neuron Auction. arXiv:2605.08326 [cs.LG] https://arxiv.org/abs/2605.08326
  26. [31]Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, Fei Huang, and Jingren Zhou. 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025). doi:10.48550/arXiv.2506.05176DOI
  27. [32]Guozhe Zhao, Qun Hu, Shiping Song, Dagui Chen, Han Zhu, Jian Xu, and Bo Zheng. 2026. LLM-Auction: Generative Auction towards LLM-Native Advertising. arXiv:2512.10551 [cs.GT] https://arxiv.org/abs/2512.10551

Paper details

vlnc:W_qr6n5n2x
Published
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

Not recorded for this paper

View statement
Looking for related papers…
Contents