arXiv AI By Eve Fleisig, Joachim Baumann, Dylan Hadfield-Menell, Dirk Hovy

Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation

Read the original on arXiv AI →

The paper "Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation" examines how arena-style rankings of language models, which rely on pairwise comparisons and the Bradley‑Terry model, can be manipulated. It identifies three attack vectors—strategic voting, strategic prompting, and strategic nomination—that can each boost a model’s rank by 15‑20 places, and combined attacks can improve a rank by up to 45 places. The authors analyze the conditions that enable these vulnerabilities and propose safeguards for any preference‑based evaluation that permits open prompting, voting, or model submission.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Oct 1

MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate

MiniRep is a reputation‑based aggregation system designed for multi‑agent debate (MAD) that remains robust even when malicious agents are present. It evaluates agents on both their current task performance and historical reputation, while preventing groups of agents with highly similar responses from dominating the final decision. Experiments on the MATH benchmark show that MiniRep consistently outperforms conventional MAD aggregation and other reputation‑based approaches across a wide range of attack scenarios.

By Jiaming Zhang, Yuwan Liu, Yue Huang, Sisi Duan