csn,daod

csn's Introduction

👋 About me

I am currently a postdoctoral researcher at the Gaoling School of Artificial Intelligence, Renmin University of China. I earned my PhD from University of Montreal, where I was mentored by Prof. Jian-Yun Nie.
I completed my master's (2019) and bachelor's (2016) degrees at Renmin University of China, under the guidance of Prof. Zhicheng Dou and Prof. Ji-Rong Wen, delving into various NLP challenges.
Research interests: Retrieval-augmented generation, large language models for information retrieval, session-based document ranking

📎 Homepages

Personal page: https://daod.github.io/
Google scholar: https://scholar.google.com/citations?user=tBqVOWsAAAAJ
DBLP: https://dblp.org/pid/71/9704-1.html

🔥 News

2024.5: We publish a new toolkit ⚡FlashRAG, which can help implement RAG methods quickly! See more details.
2024.5: Congrats! Our three papers have been accepted by ACL 2024!
2024.4: We write a new survey about generative information retrieval. See more details.
2024.1: We propose a new instruction tuning dataset (INTERS) for unlocking the power of LLMs on search tasks. See more details.
2023.11: We analyze the risk of data leakage in LLM pre-training and write a new paper to alert this problem. See more details.
2023.8: We write a new survey about applying large language models for information retrieval. See more details.
2023.8: We publish a new version of YuLan-Chat. It achieves better performance than the official LLaMA-2 and LLaMA-2-Chat on MMLU, C-Eval, and AGI-Gaokao benchmarks!

csn's People

Contributors

Stargazers

Watchers

csn's Issues

Cannot reproduce the performance on CMUDoG

Hello! Thank you for your contribution of CSN.

I used your open-sourced codes recently doing some experiments.
But when following your instruction of reproducing CSN's performance on CMUDoG using your codes and data without any revision, I couldn't obtain the expected performance.

Could you provide any suggestions about that?

The final performance has been written below as your reference.

Epoch  8 / 8
100%|██████████████████| 723180/723180 [1:03:57<00:00, 188.45it/s, loss=0.189, lr=9.77e-7]
Average loss:0.199410
Best Result: R@1: 0.054 R@2: 0.109 R@5: 0.266
use time:  524.3061871846517  min

Recommend Projects