hallucination-mitigation

[JMLR 2026] UQLM: A Python package for LLM hallucination detection using uncertainty quantification

up-to-date curated list of state-of-the-art Large vision language models hallucinations research work, papers & resources

[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Always keep your codebases ready for Agents. Improve any coding workflow by atleast 2x by maintaing a live, pluggable context layer per repo that creates and maintains Agents.md

[ACL 2024] ANAH & [NeurIPS 2024] ANAH-v2 & [ICLR 2025] Mask-DPO

FastMemory is a topological representation of text data using concepts as the primary input. It helps in improving the RAG(by replacing embedding and vectors entirely), AI memory and LLM queries by upto 100% as in the huggingface benchmarks(22+ SOTA)

[EMNLP'25] A novel alignment framework that leverages image retrieval to mitigate hallucinations in Vision Language Models.

[ICML2026] Official Implementation of "TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling"

A collection of papers on LLM/LVLM hallucination evaluation, detection, and mitigation

[ICLR 2025] Data-Augmented Phrase-Level Alignment for Mitigating Object Hallucination

[EMNLP'26] Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models

[CVPR 2025 Workshop] PAINT (Paying Attention to INformed Tokens) is a plug-and-play framework that intervenes in the self-attention of the LLM and selectively boost the visual attention informed tokens to mitigate hallucination of Vision Language Models

Official implementation for the NeurIPS 2025 paper: "FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models". A lightweight, training-free framework for modulating associative behavior in MLLMs.

Unofficial implementation of Microsoft’s Claimify Paper: extracts specific, verifiable, decontextualized claims from LLM Q&A to be used for Hallucination, Groundedness, Relevancy and Truthfulness detection

Official PyTorch implementation of "LPOI: Listwise Preference Optimization for Vision Language Models" (ACL 2025 Main)

[ACL 2026] 📷 CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding — A flexible, plug-and-play toolkit for various radiology MLLM backbones, further boosting overall performance

Oscillink — Self‑Optimizing Coherent Memory for Embedding Workflows

[NeurIPS 2025] Official implementation for ''Robust Hallucination Detection in LLMs via Adaptive Token Selection'' https://arxiv.org/abs/2504.07863

Stop hallucinations by verifying citations.

UPARIS-DS (Uncertainty-Aware Paragraph-Level Iterative Reflective Deep Search Agents) is an uncertainty-aware paragraph-level iterative reflective framework that enhances deep search agents through adaptive refinement and structured evidence synthesis.