Expect the Unexpected: FailSafe Long Context QA for Finance
Paper
•
2502.06329
•
Published
•
123
Writer
Enterprise
company
Verified
AI & ML interests
AGI, LLMs, Knowledge Graph, Palmyra, Domain Specific LLM
Recent Activity
Writer's activity
Added explanation of how combined score is calculated
#2 opened 3 days ago
by
ecw429
wassemgtk
authored
a
paper
2 days ago
Added explanation of how combined score is calculated
#2 opened 3 days ago
by
ecw429
ecw429
updated
a
Space
3 days ago
Update app.py
1
#1 opened 3 days ago
by
karsitu
Update app.py
1
#1 opened 3 days ago
by
karsitu
karsitu
updated
a
Space
3 days ago
wassemgtk
updated
a
Space
3 days ago
wassemgtk
published
a
Space
3 days ago
Fix paper link
#3 opened 8 days ago
by
nielsr
dmytro-writer
authored
2
papers
8 days ago
Add link to paper and update citation.
#2 opened 9 days ago
by
nielsr
kiranr
authored
a
paper
9 days ago
muayad
authored
a
paper
9 days ago
melisa
published
a
dataset
10 days ago
Post
1511
🔥 RAG in just a few lines of code?!
Try out our Hacker News Listener with new built-in RAG capabilities and Palmyra X 004 from the team at Writer!
This Writer Framework app:
- Scrapes up to 500 HN stories and comments
- Uploads them to a Knowledge Graph
- Enables interactive chat with the content using graph-based RAG
- Provides source attribution with every response
The best part? Setting up RAG is now incredibly simple - just a few lines of code to connect your Knowledge Graph as a tool with Palmyra X 004.
🤗 Space: samjulien/hacker-news-listener
💻 Code: https://github.com/writer/framework-tutorials/tree/main/hacker-news-social-listener
Try out our Hacker News Listener with new built-in RAG capabilities and Palmyra X 004 from the team at Writer!
This Writer Framework app:
- Scrapes up to 500 HN stories and comments
- Uploads them to a Knowledge Graph
- Enables interactive chat with the content using graph-based RAG
- Provides source attribution with every response
The best part? Setting up RAG is now incredibly simple - just a few lines of code to connect your Knowledge Graph as a tool with Palmyra X 004.
🤗 Space: samjulien/hacker-news-listener
💻 Code: https://github.com/writer/framework-tutorials/tree/main/hacker-news-social-listener
Post
3063
🔥 Introducing "Writing in the Margins (WiM)" - better inference pattern for long context LLMs that solves the Lost-in-the-Middle problem 🔥
Paper page: Writing in the Margins: Better Inference Pattern for Long Context Retrieval (2408.14906)
TL;DR
Make your model write "margin notes" as you chunk prefill the KV cache. Then ask it reread all notes before it speaks up.
Works with humans, works with AI 🤖
WiM leverages the chunked prefill of the key-value cache, which concurrently generates query-based extractive summaries at each step of the prefill that are subsequently reintegrated at the end of the computation. We term these intermediate outputs “margins”, drawing inspiration from the practice of making margin notes for improved comprehension of long contexts in human reading. We show that this technique, which adds only minimal additional computation, significantly improves LLMs long context reasoning capabilities.
Think: Every chunk has a chance to be attended to/ be at the end of the context at least once. 🎉
📊 Results:
- An average accuracy boost of 7.5% in multi-hop reasoning tasks like HotpotQA and MultiHop-RAG.
- Even a 30% increase in F1-score for summarisation-like tasks (CWE).
Plus, WiM fits seamlessly into interactive applications (think: progress bar!). It can provide real-time progress updates during data retrieval and integration, making it user-friendly and transparent - a stark contrast to feeding 1mln tokens to an LLMs and waiting 6 min for the first token. 🤯
👩💻🧑💻 Check it out and contribute to our open-source project here: https://github.com/writer/writing-in-the-margins
🧠 More about chunked prefill: https://docs.vllm.ai/en/latest/models/performance.html#chunked-prefill
Paper page: Writing in the Margins: Better Inference Pattern for Long Context Retrieval (2408.14906)
TL;DR
Make your model write "margin notes" as you chunk prefill the KV cache. Then ask it reread all notes before it speaks up.
Works with humans, works with AI 🤖
WiM leverages the chunked prefill of the key-value cache, which concurrently generates query-based extractive summaries at each step of the prefill that are subsequently reintegrated at the end of the computation. We term these intermediate outputs “margins”, drawing inspiration from the practice of making margin notes for improved comprehension of long contexts in human reading. We show that this technique, which adds only minimal additional computation, significantly improves LLMs long context reasoning capabilities.
Think: Every chunk has a chance to be attended to/ be at the end of the context at least once. 🎉
📊 Results:
- An average accuracy boost of 7.5% in multi-hop reasoning tasks like HotpotQA and MultiHop-RAG.
- Even a 30% increase in F1-score for summarisation-like tasks (CWE).
Plus, WiM fits seamlessly into interactive applications (think: progress bar!). It can provide real-time progress updates during data retrieval and integration, making it user-friendly and transparent - a stark contrast to feeding 1mln tokens to an LLMs and waiting 6 min for the first token. 🤯
👩💻🧑💻 Check it out and contribute to our open-source project here: https://github.com/writer/writing-in-the-margins
🧠 More about chunked prefill: https://docs.vllm.ai/en/latest/models/performance.html#chunked-prefill
- 2 replies
axel-writer
authored
a
paper
6 months ago
hkproj
authored
a
paper
6 months ago