Papers › Ranking Manipulation for Conversational Search Engines

Ranking Manipulation for Conversational Search Engines

5 Jun 2024arXiv:2406.03589archive 2025-07-28

Samuel Pfrommer, Yatong Bai, Tanmay Gautam, Somayeh Sojoudi

Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM context for summarization and interpretation. Recent research demonstrates that LLMs are highly vulnerable to jailbreaking and prompt injection attacks, which disrupt the safety and quality goals of LLMs using adversarial strings. This work investigates the impact of prompt injections on the ranking order of sources referenced by conversational search engines. To this end, we introduce a focused dataset of real-world consumer product websites and formalize conversational search ranking as an adversarial problem. Experimentally, we analyze conversational search rankings in the absence of adversarial injections and show that different LLMs vary significantly in prioritizing product name, document content, and context position. We then present a tree-of-attacks-based jailbreaking technique which reliably promotes low-ranked products. Importantly, these attacks transfer effectively to state-of-the-art conversational search engines such as perplexity.ai. Given the strong financial incentive for website owners to boost their search ranking, we argue that our problem formulation is of critical importance for future robustness work.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 2 repositories, 12 ran (5 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

spfrommer/ragdoll-data-pipeline officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
spfrommer/ranking_manipulation officialmentioned in papermentioned on GitHubSyntology: not harvested report
spfrommer/ranking_manipulation_data_pipeline officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
spfrommer/cse-ranking-manipulation officialmentioned on GitHubSyntology: 16 samples, 9 ran (6 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · our draft was wrong
5ran
8unverified

Licence: 20 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

spfrommer/ragdoll-data-pipeline official repository 4 samples, 3 ran (1 instrument-failed) · 1 unverified
csv_to_dict utils/file_utils.py ran · our draft was wrong licence not identified · pointer only · 09469cd52785b038 · report fixture: signature csv_file:str/0/str · returned dict · level recorded 2026-09-24
get_next_versioned_filename utils/file_utils.py ran licence not identified · pointer only · 0718bfbd86457358 · report fixture: signature folder_path:str/0/str, increment_minor:bool/0/bool, custom_major_version:NoneType/0/? · returned tuple · level recorded 2026-09-24
get_product_list utils/file_utils.py ran licence not identified · pointer only · 66b84fe0d31001cc · report fixture: signature cat_file_path:str/0/str, start_prod:int/0/int, num_prods:int/0/int · returned list · level recorded 2026-09-24
query_google_cse utils/query_utils.py unverified licence not identified · pointer only · 11aeebad7af99d72 · report
spfrommer/cse-ranking-manipulation official repository 16 samples, 9 ran (6 instrument-failed) · 7 unverified
change_extension helpers/file_utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cc1302fa5d7c53c3 · report fixture: signature path:str/0/str, new_extension:str/0/str · returned str · level recorded 2026-09-24
files_with_extension helpers/file_utils.py ran · our draft was wrong no licence file found · pointer only · 2776dd329705a63c · report fixture: signature directory:str/0/str, extension:str/0/str · returned list · level recorded 2026-09-24
format_target_message_with_docs prompts.py ran no licence file found · pointer only · 32e1ad2b0a300487 · report fixture: signature query:str/0/str, documents:list/1/str, product_models:list/1/str, product_brands:list/1/str · returned str · level recorded 2026-09-24
get_categories in 9 papers dataset.py ran · our draft was wrong no licence file found · pointer only · 690bec63359f91e1 · report fixture: signature dataset_dir:str/0/str · returned list · level recorded 2026-09-24
get_prompt_for_attacker prompts.py ran no licence file found · pointer only · c515b2aafa53de80 · report fixture: signature promoted_product_model:str/0/str, promoted_product_brand:str/0/str, promoted_document:str/0/str, max_score:int/0/int · returned str · level recorded 2026-09-24
get_prompt_for_target prompts.py ran · our draft was wrong no licence file found · pointer only · b121b8540d457313 · report fixture: signature include_ordering_prompt:bool/0/bool · returned str · level recorded 2026-09-24
remove_extension helpers/file_utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9e0c05cabd0e3ce5 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-24
truncate_string helpers/plot_utils.py ran no licence file found · pointer only · 6d8b3d2a1bc9c0d6 · report fixture: signature st:str/0/str, font_size:int/0/int, truncate_width:int/0/int · returned str · level recorded 2026-09-24
user_query dataset.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 452f1ec13ee8c27f · report fixture: signature category:str/0/str · returned str · level recorded 2026-09-24
out_original_path natural.py unverified no licence file found · pointer only · baadfaf4243bfbd3 · report
out_path adversarial.py unverified no licence file found · pointer only · f5d265cf8df739dd · report
out_rewritten_path natural.py unverified no licence file found · pointer only · 4f6c0c890b14deb3 · report
plot_original_path natural.py unverified no licence file found · pointer only · 4fd0ad8f0b061f68 · report
plots_path adversarial.py unverified no licence file found · pointer only · f01af5f656610699 · report
truncate_colormap in 8 papers adversarial.py unverified no licence file found · pointer only · 72daa2fee3baaf30 · report
upload_htmls_and_get_urls helpers/app_interface.py unverified no licence file found · pointer only · 550f868dce7d4688 · report

Tasks

Conversational SearchLanguage ModelingLanguage ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections