Comments (4)
哦哦 我明白你的意思了 你的意思是 人类语言天然的就存在evidence偏向于在首尾? 好吧,这样就难以区分哪些是真正有效的策略了。
from longbench.
谢谢你的建议。longbench中synthetic tasks是这样随机构造的,即我们把evidence的段落放在context的随机位置。在其他任务中,为了保证和真实场景分布一致,我们避免用这种人造方式改变原先的context。这种答案分布的bias在真实场景中也往往是存在的——例如文章的开头、末尾一般更加重要。
from longbench.
感谢回复,但是我试着只使用最末尾的1k token进行推理,精度和使用全量数据接近,这不合理啊。
from longbench.
In our practical testing process, we’ve encountered a similar issue.
We’ve noticed that various methods claiming to compress the sequence dimensions of KV caches (such as different heads drop different part of the sequence) and approaches for handling long sequence inference (like streamLLM) perform well on LongBench. This is because they achieve high scores by retaining only a small portion of the text at the end of the sequence. However, tasks like ‘finding a needle in a haystack’ can more accurately evaluate a model’s capabilities because they hide the ‘needle’ in different positions. Unfortunately, ‘finding a needle in a haystack’ doesn’t cover all aspects comprehensively. If possible, I hope the authors can enhance the LongBench mechanism.
from longbench.
Related Issues (20)
- 测试13b,比如百川,1*A100(80G)会OOM
- 报错TypeError: Couldn't cast array of type list<item: string> to null HOT 1
- AttributeError: 'str' object has no attribute 'to' HOT 1
- Any Implementation of Mistral-7B? HOT 1
- Llama2-7B-chat-4k测试出来结果不一样 HOT 3
- CUDA error?????? HOT 2
- 求问 Spearman correlation 是怎么计算的 HOT 1
- RuntimeError when running pred.py for Vicuna-v1.5-7B-16k HOT 2
- chatglm3-6b-32k的中文测试结果远远低于README里的benchmark HOT 5
- Include data on which passage contains answer HOT 1
- `Llama2-7B-chat-4k` on `PassageRetrieval-zh` gets `10.12` HOT 4
- Table reproduce
- 请问数据集中 avg length 是单词长度/字长度还是token个数? HOT 1
- Chinese Examples in MultiFieldQA-en HOT 1
- Loading local datasets with split=‘test’ HOT 1
- Llama2-7B-chat-4k测试出来结果不一样 HOT 2
- The "anwser" for some examples in "qasper.jsonl" is strange HOT 6
- Load dataset from hf failed HOT 4
- Code for evaluation with GPT-3.5? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from longbench.