A Knowledge Graph and a Tripartite Evaluation Framework Make Retrieval-Augmented Generation Scalable and Transparent
arxiv.org·18m
🔍Information Retrieval
Program Optimisations via Hylomorphisms for Extraction of Executable Code
drops.dagstuhl.de·23h·
Discuss: Hacker News
👑Coq Tactics
How many valid JSON strings are there?
qntm.org·6h
✅Format Verification
Emacs: Cycle through different paragraph formats: all on one line, wrapped, max one sentence per line, one sentence per line
sachachua.com·1d
📝Parsing Grammars
User Defined Types and Custom Metadata in DataFusion
datafusion.apache.org·11h·
Discuss: Hacker News
📋DFDL
OpenDataLoader-PDF: An open source tool for structured PDF parsing
github.com·14h·
Discuss: Hacker News
📄PDF Internals
Why Tables Are the Hardest Problem in Document AI
runpulse.com·1d·
Discuss: Hacker News
📄Document AI
The Database Zoo: SQL, NoSQL, and the Rise of Specialized Engines
hackernoon.com·1d
🏺Database Archaeology
Scaling Speculative Decoding with Lookahead Reasoning
hao-ai-lab.github.io·1d
🔧Reed-Solomon Decoders
Multi-Hierarchical Feature Detection for Large Language Model Generated Text
arxiv.org·18m
🤖Advanced OCR
From Chaos to Clarity: Leveraging Pydantic for Smarter AI
dev.to·23h·
Discuss: DEV
✅Archive Validation
Things in the "Context Plane" – By Shagility
agiledata.substack.com·7h·
Discuss: Substack
🔗Data Provenance
Codifying Natural Langauge Tasks
arxiv.org·1d
📋Document Grammar
Show HN: Embedding Explorer – compare text embedding models in your browser
github.com·10h·
Discuss: Hacker News
🌀Brotli Dictionary
Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics
arxiv.org·1d
📐Binary Grammars
AD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback
arxiv.org·18m
💻Programming languages
From Documents to Database: Failure Modes for Industrial Assets
arxiv.org·1d
📚Documentation Archaeology
LLM Features That Ship: Extraction, Generation, and Classification
alex-jacobs.com·12h·
Discuss: Hacker News
🌀Brotli Internals
Open Political Corpora: Structuring, Searching, and Analyzing Political Text Collections with PoliCorp
arxiv.org·1d
📄Semantic Chunking
Compositional Interface Refinement Through Subtyping in Probabilistic Session Types
arxiv.org·1d
📞Session Types