Confusing the Map for the Territory
cacm.acm.org·1d
🌍Cultural Algorithms
Scott Kim's Inversions: Dream and Level
nkanaev.com·1d·
Discuss: Hacker News
📐Mathematical Art
Prompt sensitivity is more nuanced (and useful) than we think
newsletter.aimuscle.com·14h·
Discuss: Hacker News
⚡Proof Automation
LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue
arxiv.org·1d
🔢Denotational Semantics
Outlier Analysis in Data Mining: Finding the Unusual in Your Data
dev.to·3h·
Discuss: DEV
📄Text Mining
Why Markdown Is the De Facto Standard for Prompt Engineering
dev.to·1d·
Discuss: DEV
🌳Incremental Parsing
Turning Your Documentation into Smart Responses
dev.to·4d·
Discuss: DEV
🤖Archive Automation
SESGO: Spanish Evaluation of Stereotypical Generative Outputs
arxiv.org·5h
📊Learned Metrics
Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models
arxiv.org·5h
🔍Information Retrieval
Normalisation of SWIFT Message Counterparties with Feature Extraction and Clustering
arxiv.org·3d
⚙️ABNF Mining
Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
arxiv.org·1d
🧠Intelligence Compression
Exploring and Mitigating Fawning Hallucinations in Large Language Models
arxiv.org·1d
🔗Parser Combinators
Precision Microscopy Data Augmentation via Spectral Decomposition & Generative Adversarial Networks
dev.to·7h·
Discuss: DEV
📄Document Digitization
SIGMUS: Semantic Integration for Knowledge Graphs in Multimodal Urban Spaces
arxiv.org·1d
🎭Cultural Informatics
Binary Quantization For LLMs Through Dynamic Grouping
arxiv.org·5h
💻Local LLMs
Expanding the WMT24++ Benchmark with Rumantsch Grischun, Sursilvan, Sutsilvan, Surmiran, Puter, and Vallader
arxiv.org·5h
🔍Z3 Parsing
Creating a Twitter Sentiment Analysis NLP Model For Video Games
dev.to·2d·
Discuss: DEV
🤖Grammar Induction
ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics
arxiv.org·1d
🔍Information Retrieval
Semantic Parsing for Question Answering over Knowledge Graphs
arxiv.org·1d
🧮Prolog Parsing
Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models
arxiv.org·1d
🤖Advanced OCR