From c62bcdb24d646f2cd9037a7ea1c7d22fb6cd7eca Mon Sep 17 00:00:00 2001 From: Jack Tang <73820234+McJackTang@users.noreply.github.com> Date: Tue, 15 Aug 2023 15:55:09 +0800 Subject: [PATCH] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 4cf9e7f..c35e2ed 100644 --- a/README.md +++ b/README.md @@ -23,13 +23,13 @@ LongBench includes 13 English tasks, 5 Chinese tasks, and 2 code tasks, with the | Code Completion | - | - | 2 | ## 🔠Table of Contents -- [Leaderboard](#Leaderboard) +- [🖥ï¸Leaderboard](#🖥ï¸Leaderboard) - [How to evaluate on LongBench](#how-to-evaluate-on-LongBench) - [Evaluation Result on Each Dataset](#evaluation-result-on-each-dataset) - [Acknowledgement](#acknowledgement) - [Citation](#citation) -## ðŸ–¥ï¸ Leaderboard +## 🖥ï¸Leaderboard Here is the average scores (%) on the main task categories in both Chinese and English languages under the Zero-shot scenario. Please refer to this [link](task.md) for the evaluation metrics used for each task. > Note: For text exceeding the processing length capability of the model, we truncate from the middle of the text, preserving information from the beginning and end, in accordance with the observations from [Lost in the Middle](https://arxiv.org/abs/2307.03172). Experiments show that this truncation method has the least impact on model performance. -- GitLab