Skip to content

Generative-Engine-Marketing/GEM-Bench

View on GitHub ↗Related repositories →

First comprehensive benchmark for Generative Engine Marketing (GEM), an emerging field that focuses on monetizing generative AI by seamlessly integrating advertisements into Large Language Model (LLM) responses. Our work addresses the core problem of ad-injected response (AIR) generation and provides a framework for its evaluation.

active 2025-10-022026-07-04 (UTC)

Complete coverage26,483 / 26,483 hourly files (100%) · 2 absent upstream2023-08-152026-08-22 (UTC)
Events
35
Pushes
15
Pull requests
0
Issues
4
Stars
10
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 276 days from 2025-10-02 to 2026-07-04. Pushes: 15 total, peak 12 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 4 total, peak 3 in a day. Comments: 4 total, peak 3 in a day. Stars: 10 total, peak 2 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
Qingbolan231504

Recent activity

Latest issues, pull requests and releases

  • Issue comment#8Qingbolan2025-11-16 13:07
    For Figure 2, are the shown weaknesses of Ad-Chat due to inherent limitations of prompt-based insertion, or mainly due to the specific prompt used? Were alternative prompt designs evaluated?
  • Issue#10Qingbolan2025-11-14 16:45
    The evaluation relies entirely on LLM-as-judge scoring without any human annotation or preference validation, making it unclear how well the measured metrics align with real user perception.
  • Issue comment#9Qingbolan2025-11-13 16:18
    Results are only presented with niche LLM of doubao-1.5
  • Issue comment#9Qingbolan2025-11-13 15:40
    Results are only presented with niche LLM of doubao-1.5
  • Issue comment#6Qingbolan2025-11-13 14:38
    The chatbot datasets contain only 10 and 100 queries, respectively, which may limit statistical robustness and generalizability to diverse domains.
  • Issue#7Qingbolan2025-11-13 08:48
    How sensitive are the results to the number of ads (k > 1) inserted into each response?
  • Issue#9Qingbolan2025-11-13 08:48
    Results are only presented with niche LLM of doubao-1.5
  • Issue#8Qingbolan2025-11-13 08:38
    For Figure 2, are the shown weaknesses of Ad-Chat due to inherent limitations of prompt-based insertion, or mainly due to the specific prompt used? Were alternative prompt designs evaluated?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 10 stars here means stars gained during the window, not the repo's star count.