# InterPol: De-anonymizing LM Arena via Interpolated Preference Learning

arXiv: https://arxiv.org/abs/2603.15220 · HTML: https://mlsanity.com/paper/2603.15220/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [A Watermark for Large Language Models](https://mlsanity.com/paper/2301.10226/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Data Contamination: From Memorization to Exploitation](https://mlsanity.com/paper/2203.08242/) (2022)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [Instructional Fingerprinting of Large Language Models](https://mlsanity.com/paper/2401.12255/) (2024)
- [The Leaderboard Illusion](https://mlsanity.com/paper/2504.20879/) (2025)
- [Elo Uncovered: Robustness and Best Practices in Language Model Evaluation](https://mlsanity.com/paper/2311.17295/) (2023)
- [From Text to Source: Results in Detecting Large Language Model-Generated Content](https://mlsanity.com/paper/2309.13322/) (2023)
- [Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards](https://mlsanity.com/paper/2501.07493/) (2025)
- [Improving Your Model Ranking on Chatbot Arena by Vote Rigging](https://mlsanity.com/paper/2501.17858/) (2025)
- [Reverse Engineering Configurations of Neural Text Generation Models](https://mlsanity.com/paper/2004.06201/) (2020)
- [Challenges in Trustworthy Human Evaluation of Chatbots](https://mlsanity.com/paper/2412.04363/) (2024)

## Abstract (arXiv)

Strict anonymity of model responses is a key for the reliability of voting-based leaderboards, such as LM Arena. While prior studies have attempted to compromise this assumption using simple statistical features like TF-IDF or bag-ofwords, these methods often lack the discriminative power to distinguish between stylistically similar or within-family models. To overcome these limitations and expose the severity of vulnerability, we introduce INTERPOL, a model-driven identification framework that learns to distinguish target models from others using interpolated preference data. Specifically, INTERPOL captures deep stylistic patterns that superficial statistical features miss by synthesizing hard negative samples through model interpolation and employing an adaptive curriculum learning strategy. Extensive experiments demonstrate that INTERPOL significantly outperforms existing baselines in identification accuracy. Furthermore, we quantify the real-world threat of our findings through ranking manipulation simulations on Arena battle data.