LLM hallucination mitigation

Quivr is a framework for building retrieval-augmented generation pipelines that connect large language models to custom knowledge bases. It serves as a generative AI integration layer that abstracts the process of transforming diverse document sources into searchable context for AI responses. The project orchestrates the end-to-end flow between document ingestion, vector storage management, and model provider interfaces. It features a vector-store-agnostic retrieval system and a modular API layer that allows for flexible switching between different generative model providers. The system cove

This project is a collection of reference implementations and recipes for deploying, fine-tuning, and running inference with Llama large language models. It serves as a toolkit and implementation guide for adapting pre-trained models to specific tasks and domain-specific datasets. The repository provides frameworks for developing retrieval augmented generation pipelines to ground model responses in external data. It includes guides for executing quantized inference to reduce memory usage and increase processing speed. The toolkit covers a broad range of capabilities including parameter-effic

AutoRAG is an automation layer and optimization tool for retrieval-augmented generation. It provides a framework for measuring pipeline performance through an evaluation system and an automated search strategy that identifies the most effective combinations of retrieval and generation modules. The system distinguishes itself through AutoML-style optimization, using hyperparameter grid searches and automated trials to find the highest performing architectural configuration for a specific dataset. It includes a specialized dataset generator that creates synthetic question-answer pairs and groun

Evals is a framework designed for automating, managing, and executing repeatable benchmarking suites to analyze the quality and performance of language models. It provides a platform for running standardized tests to measure model accuracy and track behavioral changes over time. The system distinguishes itself through a modular architecture that uses a standardized adapter layer to normalize inputs and outputs, allowing different models to be swapped and tested interchangeably. It supports the creation of custom benchmarks using proprietary data, enabling quality assurance on sensitive tasks

Guardrails is a Python SDK that wraps calls to large language models with configurable validation pipelines, corrective actions, and structured output generation. It provides a unified API layer that connects to over 100 language models, applying consistent validation, streaming, and error-handling across providers. The framework validates and corrects model responses against safety and quality rules, detecting and mitigating risks in both inputs and outputs using pre-built and custom validators. The project distinguishes itself through a validator-pipeline architecture that sequentially appl

Giskard is an evaluation framework, testing library, and quality monitoring system for large language models and AI agents. It serves as a toolkit for quantifying model performance and reliability, providing specialized capabilities for validating retrieval-augmented generation pipelines. The project distinguishes itself through an automated red teaming tool and security scanner designed to identify vulnerabilities, prompt injections, and safety risks. It utilizes adversarial probing and synthetic edge case generation to quantify model robustness and detect information disclosure. The platfo

Opik is an observability and evaluation platform designed for generative AI applications and agentic workflows. It provides a centralized environment for tracing execution flows, managing prompt templates, and monitoring production performance, allowing teams to gain visibility into complex model interactions and tool usage without requiring manual application code changes. The platform distinguishes itself through its integrated approach to the AI development lifecycle, combining distributed trace instrumentation with automated evaluation frameworks. It supports model-as-a-judge scoring, syn

Deepeval is a framework for testing and evaluating large language model applications. It provides a suite of tools for executing automated regression tests, validating model output quality against defined standards, and tracing the execution of complex agent workflows. By integrating these capabilities into development pipelines, the platform ensures consistent performance and reliability throughout the software lifecycle. The platform distinguishes itself through its focus on programmatic validation and observability. It utilizes secondary language models to score output quality and employs

Ragas is an evaluation framework designed to measure the performance of retrieval-augmented generation pipelines and autonomous agent workflows. It provides a comprehensive suite of tools for benchmarking system outputs, utilizing language models as automated judges to score performance against defined rubrics and reference data. By standardizing inputs, retrieved contexts, and generated responses into a unified schema, the project enables consistent analysis across complex AI applications. The framework distinguishes itself through its ability to generate synthetic test datasets from existin

NeMo-Guardrails is a toolkit for adding programmable safety constraints and dialogue boundaries to large language model conversational systems. It functions as security middleware that intercepts inputs and outputs to block prompt injections, jailbreaks, and sensitive data leaks, while providing a conversational dialogue manager to define structured interaction flows through configuration files. The framework includes a hallucination filter to screen model outputs for factual accuracy and a specialized modeling language for defining conversational flows and constraints. It provides capabiliti

DSPy is a declarative programming framework designed for building complex language model applications. It treats model interactions as modular, composable programs, allowing developers to define task logic through typed class schemas rather than relying on manually written prompts. By organizing workflows into hierarchical, reusable Python objects, the framework enables the construction of sophisticated AI systems that manage state and execution flow independently. The framework distinguishes itself through an automated optimization engine that iteratively refines prompt instructions and few-

An automatic MLLM hallucination detection framework

CVPR 2025 Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention

CVPR 2024 Highlight Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models

ICML 2024 Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"

Guidance is a control framework and generation orchestrator for large language models. It provides a programming layer to steer model outputs through structured templates, schema enforcement, and logical flow management. The framework distinguishes itself by interleaving model generation with local code execution, enabling the use of loops and conditional branching within a single session. It employs grammar-based token constraints and regular expressions to force models to sample only from tokens that satisfy a specific structural format, ensuring strict adherence to predefined data models.

Evaluation and Tracking for LLM Experiments and AI Agents

ICML 2025 Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models'.

✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models

ACL 2024 Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models. Detect and mitigate object hallucinations in LVLMs by itself through logical closed loops.

ECCV 2024 Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

Aligning LMMs with Factually Augmented RLHF

ACL 2024 Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models. Detect and mitigate object hallucinations in LVLMs by itself through logical closed loops.

Finegrained CLIPScore to detect object hallucination

mPLUG-HalOwl: Multimodal Hallucination Evaluation and Mitigating

NeurIPS 2024 Mitigating Object Hallucination via Concentric Causal Attention

ICLR 2024 Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)

| 🔥 News | 🤖️ Demo | 🚀 Quick Start | 💾 Benchmark | 📖 Docs |

Fiddler Auditor is a tool to evaluate language models.

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

MedHallTune: A Benchmark and Instruction Tuning Dataset for Mitigating Medical Hallucination in Vision-Language Models