Menu

Breaking 0.669 to Reach Top 5 in Kaggle's "Name That LLM": The Decoy Trap, Dual-SVC & Sequence Encoders
📰

Breaking 0.669 to Reach Top 5 in Kaggle's "Name That LLM": The Decoy Trap, Dual-SVC & Sequence Encoders

DEV Community: datascience·Jun Matsui·9 days ago
#qlP7bAGB
#devtodatascience#science#devto#dev#flash
Reading 0:00
15s threshold

Breaking 0.669 to Reach Top 5 in Kaggle's "Name That LLM"

How we uncovered the public "decoy camouflage", introduced a high-diversity DeBERTa-v3 sequence head, and recalibrated Sinkhorn optimal transport to push beyond the 0.672 plateau.

1. The Challenge: Who Wrote That Passage?

In Kaggle’s Name That LLM competition, participants are tasked with attributing short text passages to one of 18 generative language models spanning six distinct model families:

Anthropic : Claude Fable 5, Opus 4.6, Opus 4.8, Opus 5, Sonnet 5

Google : Gemini 3.1 Pro Preview, 3.6 Flash, 3.7 Flash, 3.8 Flash

Zhipu AI : GLM-5.3, GLM-5.3 Flash

OpenAI : GPT-5.5, GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-6 Astra

Moonshot AI : Kimi K3

Alibaba : Qwen 3.8 Max

The metric is Balanced Accuracy Score (macro-average recall per class).…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.