Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.14256 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908544865927168 |
|---|---|
| author | Dutta, Arka Majumdar, Agrik Biswas, Sombrata Das, Dipankar Bandyopadhyay, Sivaji |
| author_facet | Dutta, Arka Majumdar, Agrik Biswas, Sombrata Das, Dipankar Bandyopadhyay, Sivaji |
| contents | This paper proposes a comprehensive framework for the generation of covert advertisements within Conversational AI systems, along with robust techniques for their detection. It explores how subtle promotional content can be crafted within AI-generated responses and introduces methods to identify and mitigate such covert advertising strategies. For generation (Sub-Task~1), we propose a novel framework that leverages user context and query intent to produce contextually relevant advertisements. We employ advanced prompting strategies and curate paired training data to fine-tune a large language model (LLM) for enhanced stealthiness. For detection (Sub-Task~2), we explore two effective strategies: a fine-tuned CrossEncoder (\texttt{all-mpnet-base-v2}) for direct classification, and a prompt-based reformulation using a fine-tuned \texttt{DeBERTa-v3-base} model. Both approaches rely solely on the response text, ensuring practicality for real-world deployment. Experimental results show high effectiveness in both tasks, achieving a precision of 1.0 and recall of 0.71 for ad generation, and F1-scores ranging from 0.99 to 1.00 for ad detection. These results underscore the potential of our methods to balance persuasive communication with transparency in conversational AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14256 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JU-NLP at Touché: Covert Advertisement in Conversational AI-Generation and Detection Strategies Dutta, Arka Majumdar, Agrik Biswas, Sombrata Das, Dipankar Bandyopadhyay, Sivaji Computation and Language Artificial Intelligence This paper proposes a comprehensive framework for the generation of covert advertisements within Conversational AI systems, along with robust techniques for their detection. It explores how subtle promotional content can be crafted within AI-generated responses and introduces methods to identify and mitigate such covert advertising strategies. For generation (Sub-Task~1), we propose a novel framework that leverages user context and query intent to produce contextually relevant advertisements. We employ advanced prompting strategies and curate paired training data to fine-tune a large language model (LLM) for enhanced stealthiness. For detection (Sub-Task~2), we explore two effective strategies: a fine-tuned CrossEncoder (\texttt{all-mpnet-base-v2}) for direct classification, and a prompt-based reformulation using a fine-tuned \texttt{DeBERTa-v3-base} model. Both approaches rely solely on the response text, ensuring practicality for real-world deployment. Experimental results show high effectiveness in both tasks, achieving a precision of 1.0 and recall of 0.71 for ad generation, and F1-scores ranging from 0.99 to 1.00 for ad detection. These results underscore the potential of our methods to balance persuasive communication with transparency in conversational AI. |
| title | JU-NLP at Touché: Covert Advertisement in Conversational AI-Generation and Detection Strategies |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.14256 |