⚖️ Inference Rules - 2601 · Scour

Formalized Information Needs Improve Large-Language-Model Relevance Judgments 🔍RAG

arxiv.org·3d

Incremental Lambda Calculus 🔗Dependent Types

inc-lc.github.io·5h·Hacker News

Structural Effects of the Knowledge Innovation System on AI Judgment Patterns: — 3 Models × 4 Conditions × 5 Questions × 30 Repetitions 🔄Systems Thinking

zenodo.org·3d·Hacker News

LLM Evaluation as Tensor Completion: Low Rank Structure and Semiparametric Efficiency 🐍Mamba SSM

arxiv.org·2d

Reflection On Recursion • 2 🪜Recursive Descent

inquiryintoinquiry.com·23h

Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge ✨Effect Inference

arxiv.org·2d

mm0/mm0-rs/mmc.md at master 📏Linear Types

github.com·8h·Hacker News

Operational Noncommutativity in Sequential Metacognitive Judgments 🐍Mamba SSM

arxiv.org·2d

Paper close reading: "Why Language Models Hallucinate" 🪜Recursive Descent

lesswrong.com·4d·Hacker News

Tax logic evaluation with Prolog · mthom scryer-prolog 📊Datalog

github.com·2d·Hacker News

Structured Multi-Criteria Evaluation of Large Language Models with Fuzzy Analytic Hierarchy Process and DualJudge 💬Prompt Engineering

arxiv.org·3d

The Rocq Prover 9.2 documentation ✨Gleam

rocq-prover.org·3d·Hacker News

How Annotation Trains Annotators: Competence Development in Social Influence Recognition 🔗Network Motifs

arxiv.org·4d

Post-Penultimate Conditional Syntax 🔬programming language theory

joel.place·5d·Hacker News

Capture-Quiet Decomposition: A Verification Theorem for Chess Endgame Tablebases ✓Formal Methods

arxiv.org·10h·Hacker News

ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning ⚡Automated Reasoning

arxiv.org·1d

An introduction to Turing machines and computation 🎯Finite Automata

max-amb.github.io·6d·Hacker News

Toward a Tractability Frontier for Exact Relevance Certification 🌳Pattern Match Compilation

arxiv.org·1d

Detecting and Explaining (In-)equivalence of Context-Free Grammars 🔍Type Inference

arxiv.org·1d

Pramana: Fine-Tuning Large Language Models for Epistemic Reasoning through Navya-Nyaya 🧠Symbolic AI

arxiv.org·2d

Loading more...