Detecting Generated Native Ads in Conversational Search
- URL: http://arxiv.org/abs/2402.04889v2
- Date: Tue, 30 Apr 2024 09:15:42 GMT
- Title: Detecting Generated Native Ads in Conversational Search
- Authors: Sebastian Schmidt, Ines Zelch, Janek Bevendorff, Benno Stein, Matthias Hagen, Martin Potthast,
- Abstract summary: Conversational search engines such as YouChat and Microsoft Copilot use large language models (LLMs) to generate responses to queries.
It is only a small step to also let the same technology insert ads within the generated responses.
Inserted ads would be reminiscent of native advertising and product placement.
- Score: 33.5694271503764
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Conversational search engines such as YouChat and Microsoft Copilot use large language models (LLMs) to generate responses to queries. It is only a small step to also let the same technology insert ads within the generated responses - instead of separately placing ads next to a response. Inserted ads would be reminiscent of native advertising and product placement, both of which are very effective forms of subtle and manipulative advertising. Considering the high computational costs associated with LLMs, for which providers need to develop sustainable business models, users of conversational search engines may very well be confronted with generated native ads in the near future. In this paper, we thus take a first step to investigate whether LLMs can also be used as a countermeasure, i.e., to block generated native ads. We compile the Webis Generated Native Ads 2024 dataset of queries and generated responses with automatically inserted ads, and evaluate whether LLMs or fine-tuned sentence transformers can detect the ads. In our experiments, the investigated LLMs struggle with the task but sentence transformers achieve precision and recall values above 0.9.
Related papers
- RuAG: Learned-rule-augmented Generation for Large Language Models [62.64389390179651]
We propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules.
We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks.
arXiv Detail & Related papers (2024-11-04T00:01:34Z) - Automating Knowledge Discovery from Scientific Literature via LLMs: A Dual-Agent Approach with Progressive Ontology Prompting [59.97247234955861]
We introduce a novel framework based on large language models (LLMs) that combines a progressive prompting algorithm with a dual-agent system, named LLM-Duo.
Our method identifies 2,421 interventions from 64,177 research articles in the speech-language therapy domain.
arXiv Detail & Related papers (2024-08-20T16:42:23Z) - Ranking Manipulation for Conversational Search Engines [7.958276719131612]
We study the impact of prompt injections on the ranking order of sources referenced by conversational search engines.
We present a tree-of-attacks-based jailbreaking technique which reliably promotes low-ranked products.
arXiv Detail & Related papers (2024-06-05T19:14:21Z) - Scaling Up LLM Reviews for Google Ads Content Moderation [22.43127685744644]
Large language models (LLMs) are powerful tools for content moderation, but their inference costs and latency make them prohibitive for casual use on large datasets.
This study proposes a method for scaling up LLM reviews for content in Google Ads.
arXiv Detail & Related papers (2024-02-07T23:47:02Z) - Generative Context-aware Fine-tuning of Self-supervised Speech Models [54.389711404209415]
We study the use of generative large language models (LLM) generated context information.
We propose an approach to distill the generated information during fine-tuning of self-supervised speech models.
We evaluate the proposed approach using the SLUE and Libri-light benchmarks for several downstream tasks: automatic speech recognition, named entity recognition, and sentiment analysis.
arXiv Detail & Related papers (2023-12-15T15:46:02Z) - Check Your Facts and Try Again: Improving Large Language Models with
External Knowledge and Automated Feedback [127.75419038610455]
Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks.
This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
arXiv Detail & Related papers (2023-02-24T18:48:43Z) - TSI: an Ad Text Strength Indicator using Text-to-CTR and
Semantic-Ad-Similarity [16.10904771281746]
We propose an ad text strength indicator (TSI) which: (i) predicts the click-through-rate (CTR) for an input ad text, (ii) fetches similar existing ads to create a neighborhood around the input ad, and compares the predicted CTRs in the neighborhood to declare whether the input ad is strong or weak.
As suggestions for ad text improvement, TSI shows anonymized versions of superior ads (higher predicted CTR) in the neighborhood.
arXiv Detail & Related papers (2021-08-18T16:24:40Z) - Learning to Create Better Ads: Generation and Ranking Approaches for Ad
Creative Refinement [26.70647666598025]
We study approaches to refine the given ad text and image by: (i) generating new ad text, (ii) recommending keyphrases for new ad text, and (iii) recommending image tags (objects in image)
Based on A/B tests conducted by multiple advertisers, we form pairwise examples of inferior and superior ad creatives.
We also share broadly applicable insights from our experiments using data from the Yahoo Gemini ad platform.
arXiv Detail & Related papers (2020-08-17T16:46:28Z) - Do Interruptions Pay Off? Effects of Interruptive Ads on Consumers
Willingness to Pay [79.9312329825761]
We present the results of a study designed to measure the impact of interruptive advertising on consumers willingness to pay for products bearing the advertiser's brand.
Our results contribute to the research on the economic impact of advertising, and introduce a method of measuring actual (as opposed to self-reported) willingness to pay in experimental marketing research.
arXiv Detail & Related papers (2020-05-14T09:26:57Z) - Query-Variant Advertisement Text Generation with Association Knowledge [21.18443320935013]
Traditional text generation methods tend to focus on the general searching needs with high frequency.
We propose a query-variant advertisement text generation task that aims to generate candidate advertisement texts for different web search queries.
Our model can make use of various personalized needs in queries and generate query-variant advertisement texts.
arXiv Detail & Related papers (2020-04-14T12:04:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.