NVIDIA/logits-processor-zoo

A guidance language for controlling large language models.

Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors

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

Adding guardrails to large language models.

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Verbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. Model-agnostic framework with CLI/API for creative writing, synthetic data generation, and dialogue simulation.

A library for prompt engineering and optimization (SAMMO = Structure-aware Multi-Objective Metaprompt Optimization)

Antidoom generates and trains targeted preference data for reducing model repetition loops (doom loops).

An Automatic Prompt Optimization Framework for Large Language Models