constrained-decoding

Query language for blending SQL and local language models across structured + unstructured data, with type constraints.

Reproduction Package for the paper "Type-Constrained Code Generation with Language Models" [PLDI 2025]

For our ICRA 2025 paper 🏆 "SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models" by Yi Wu, Zikang Xiong, Yiran Hu, Shreyash Iyengar, Nan Jiang, Aniket Bera, Lin Tan, and Suresh Jagannathan. (🏆 Best Paper Award Finalist!)

Code for paper "Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation" EMNLP 2021 and "Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation" arXiv 2020

A tool-calling layer, not a language model — your schemas in, validated calls out, at 48M parameters. Malformed JSON, invented parameter names, and undeclared tools are structurally unreachable on any catalog. Adapt it to your own catalog; 11 negative results included.

[Pytorch] Efficient tokenization for recommendations and generative retrieval. Inspired by STATIC decoding from "Vectorizing the Trie"

Speculative grammar backtracking algorithm for LLM decoding conforming to some lark context-free grammar (CFG)

🤖 AI-powered function calling engine using a LLM to convert natural language prompts into validated JSON function calls.

Context-Free Grammar-guided Generation of FHIR Resources Using Large Language Models (MIE 2026)

A function calling tool that translates natural language prompts into structured function calls using a small LLM and constrained decoding

VibeDrift - Run any LLM on your own hardware. Bypass the VRAM wall with CPU/RAM inference, MOE expert offloading, and 4-bit quantization. No Cloud, no Subscription.

Reproduction & re-implementation of the AloLab paper (arXiv:2605.02363): closing the structured-output reliability gap in small LLMs via iterative black-box prompt optimization. GSM8K, 4 models, ablations, McNemar significance.

Artifact-backed evaluation of how structured-output contracts change LLM semantics, validity, and execution outcomes.

Call-Me-Maybe is a natural language to function call generator system using the power of AI, developed in Python. Demonstrating the technique known as Constrained Decoding where and LLM's output is forced to adhere to predefined set of rules.

Deterministic Procedural JSON Generation via a 0.6B Parameter Language Model

ServiceNow → GBNF grammar + iii worker generator | Open-source deterministic AI connector

Evidence-coded map of constrained decoding, structured generation, guarantees, systems costs, and evaluation for language models.

TexLM: Synthesizing Reliable Latex Matrix from Natural Language Input

Grammar-aided Constrained Decondig for self-aligned LLM with SFT and GRPO

Constrained decoding for reliable function calling with small language models.