🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Over the recent weeks, an epic collaboration among some of the best practitioners in this space has brought us a three-part series of "What We Learned from a Year of Building with LLMs" on O'Reilly Media! In this three-part series, Eugene Yan, Bryan Bischof fka Dr. Donut, Charles 🎉 Frye,

🚨 Happy to say that I'll be presenting our work (w/Sean MacAvaney & Debasis Ganguly) "Top-Down Partitioning for Efficient List-Wise Ranking" at ReNeuIR Workshop @ SIGIR 2025 in Washington! here's a pre-print with updates coming soon: arxiv.org/abs/2405.14589 #SIGIR2024

Large Language Models Must Be Taught to Know What They Don't Know abs: arxiv.org/abs/2406.08391 Prompting is not enough for LLMs to produce accurate estimates of its uncertainty of its responses, but can be finetuned with as little as 1000 examples and outperform baselines for

📚 Awesome Information Retrieval 🔍 I’ve compiled a list of some of my favorite IR papers from the past few years. If you’re new to the field and want to understand how Transformer-based retrieval models work before building your RAG application, this should serve as a great

APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking Proposes a novel automatic prompt engineering algorithm for zero-shot passage relevance ranking, outperforming manual prompts across various LLMs. 📝arxiv.org/abs/2406.14449 👨🏽‍💻github.com/jincan333/APEER

Improving Retrieval in LLMs by Finetuning on Synthetic Data Proposes a fine-tuning approach to improve the accuracy of retrieving information in LLMs while maintaining reasoning capabilities over long-context inputs. The fine-tuning dataset comprises numerical dictionary

Blog post on DSPy

OpenAI provides a comprehensive guide on enhancing the accuracy of Large Language Models (LLMs), emphasizing methods to improve response correctness and consistency. Rather than approaching LLM accuracy optimization as a straightforward, linear process that progresses from

New to fine-tuning LLMs? Confused by all the jargon? Me, too. So, I did a little deep dive into LLM fine-tuning. Here’s what I understood:

Your LLM is only as good as how robust your prompting method is. Seems you can enhance the robustness of LLMs by "prompting out" irrelevant information from context. Think of it as a self-mitigation process that first identifies the irrelevant information and then filters it

Graph RAG Works Better Than Standard RAG GraphRAG leverages structural information across entities to enable more precise and comprehensive retrieval, capturing relational knowledge and facilitating more accurate, context-aware responses. This improves the accuracy of standard

A useful collection of Prompt Engineering resource released from Anthropic for building on Anthropic API.

Top RAG Papers of the Week [1] Meta Knowledge for Retrieval Augmented Large Language Models [2] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation [3] Graph Retrieval-Augmented Generation: A Survey [4] CommunityKG-RAG: Leveraging

This Python tool looks super useful to crawl websites and convert data into LLM-ready markdown or structured data. I find myself doing this a lot and most of the time it is a tedious effort. Great to see a service that does data extraction catered for LLM-based pipelines.

RAG vs. Long-Context LLMs I have yet to see a convincing paper or technical blog showing that long-context LLMs can or will replace RAG. So far I've seen specific long-context applications where long-context LLMs thrive and current retrieval benchmarks are not convincing. This

Here's why ColBERT embeddings are all the rage right now (at an intuitive level): You probably already know that vector search is pretty cool. • It allows you to search for things semantically. • It's robust to synonyms. But do you know what sucks about vector search? It

If you embed an entire document, you'll lose retrieval precision. If you chunk a document, you'll lose contextual information between chunks. These are some concerns when you're building long-context RAG applications. But "Late chunking" may just be the sweet spot in the

Nature's guide on how to write effective abstracts

The Transformer's decoder clearly explained 👇🏻

Professor Edward H.Sargent a Canadian Scientist, who published many papers in top journals i.e., #science and #Nature. He wrote 10 tips on how to write papers. 𝗣𝗵𝗗𝘃𝗶𝗯𝗲 PhD Voice - Independently Run Labiofy #PhDposition #phdlife #PhD #postdoc #chemtwitter #Science #AcademicChatter