# Loki: An Open-Source Tool for Fact Verification

arXiv: https://arxiv.org/abs/2410.01794 · HTML: https://mlsanity.com/paper/2410.01794/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [On the Risk of Misinformation Pollution with Large Language Models](https://mlsanity.com/paper/2305.13661/) (2023)
- [Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers](https://mlsanity.com/paper/2311.09000/) (2023)
- [Factuality of Large Language Models: A Survey](https://mlsanity.com/paper/2402.02420/) (2024)
- [OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs](https://mlsanity.com/paper/2408.11832/) (2024)

## Built on by (most cited first, 16 of 16)

- [FIRE: Fact-checking with Iterative Retrieval and Verification](https://mlsanity.com/paper/2411.00784/) (2024)
- [ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking](https://mlsanity.com/paper/2510.13842/) (2025)
- [DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent](https://mlsanity.com/paper/2603.01152/) (2026)
- [VeriTaS: The First Dynamic Benchmark for Multimodal Automated Fact-Checking](https://mlsanity.com/paper/2601.08611/) (2026)
- [UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking](https://mlsanity.com/paper/2505.15063/) (2025)
- [Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System](https://mlsanity.com/paper/2508.06059/) (2025)
- [Proof-of-Guardrail in AI Agents and What (Not) to Trust from It](https://mlsanity.com/paper/2603.05786/) (2026)
- [Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification](https://mlsanity.com/paper/2506.07446/) (2025)
- [ShortCheck: Checkworthiness Detection of Multilingual Short-Form Videos](https://mlsanity.com/paper/2509.20467/) (2025)
- [Can LLMs extract human-like fine-grained evidence for evidence-based fact-checking?](https://mlsanity.com/paper/2511.21401/) (2025)
- [Examining the Metrics for Document-Level Claim Extraction in Czech and Slovak](https://mlsanity.com/paper/2511.14566/) (2025)
- [TrackList: Tracing Back Query Linguistic Diversity for Head and Tail Knowledge in Open Large Language Models](https://mlsanity.com/paper/2511.21006/) (2025)
- [TAIGR: Towards Modeling Influencer Content on Social Media via Structured, Pragmatic Inference](https://mlsanity.com/paper/2601.20032/) (2026)
- [ViX-Ray: A Vietnamese Chest X-Ray Dataset for Vision-Language Models](https://mlsanity.com/paper/2603.15513/) (2026)
- [CAAFC: Chronological Actionable Automated Fact-Checker for misinformation / non-factual hallucination detection and correction](https://mlsanity.com/paper/2605.12436/) (2026)
- [WildSEEK: Evaluating Language Models for Information-Seeking](https://mlsanity.com/paper/2608.30683/) (2026)

## Abstract (arXiv)

We introduce Loki, an open-source tool designed to address the growing problem of misinformation. Loki adopts a human-centered approach, striking a balance between the quality of fact-checking and the cost of human involvement. It decomposes the fact-checking task into a five-step pipeline: breaking down long texts into individual claims, assessing their check-worthiness, generating queries, retrieving evidence, and verifying the claims. Instead of fully automating the claim verification process, Loki provides essential information at each step to assist human judgment, especially for general users such as journalists and content moderators. Moreover, it has been optimized for latency, robustness, and cost efficiency at a commercially usable level. Loki is released under an MIT license and is available on GitHub. We also provide a video presenting the system and its capabilities.