🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

GPT powered sorting using structured output

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

Enforce the output format (JSON Schema, Regex etc) of a language model

Formatron empowers everyone to control the format of language models' output with minimal overhead.

A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.

Leetcode for Pytorch

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Structured Outputs

[EMNLP 2020] Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)

Multilingual Named Entity Recognition by XLM-Roberta model with CRF

JavaScript library for working with automata and grammars for regular and context-free languages

Code for "Do GPTs Produce Less Literal Translations?"

NumPy & SciPy for GPU

Information extraction from English and German texts based on predicate logic

Open German WordNet

GermaNet API for Python

The code to recreate these textual adversaries

Accompanying repository of our paper "Kamp, J., Beinborn, L., Fokkens, A. (2023). Dynamic Top-K Estimation Consolidates Disagreement between Feature Attribution Methods."

[NAACL 24] Extracting Lexical Features from Dialects via Interpretable Dialect Classifiers

utilities for decoding deep representations (like sentence embeddings) back to text

BertViz: Visualize Attention in Transformer Models

This is a monolingual English corpus of native, non-native and (human) translated texts extracted from the European Parliament.

A beautiful, simple, clean, and responsive Jekyll theme for academics

A static website compiler library in Haskell

A framework to learn cross-lingual word embedding mappings