Method
Hallucination detection
Detecting unsupported claims (SelfCheckGPT, semantic entropy, fact-checking).
11 cases from 9 companies apply Hallucination detection. 4 report results in production.
Typical tasks: Evaluate models, Answer questions over data, Build an assistant over internal docs, Reduce ML cost and 2 more. Companies: Netflix, Zomato, HSE University, Gusto, DoorDash, Yandex and 3 more. Often combined with: LLM-as-a-judge, LLM cascade, Evaluation regression gate, Human in the loop, RAG and 32 more.
| Fact-Checking at Scale: Building a More Accurate and Efficient Synopsis Factuality System | media-streaming | 2026-11 | |
| Building Gavel: AI evaluation infrastructure across Eternal | food-delivery | 2026-10 | |
| Anthropic + Adidas + Databricks: Unlocking 400 Hours of Productivity Weekly with Conversational AI | retail | 2026-06 | |
| Adaptive Summarization of News Articles Using a Sliding Window and LLM-as-a-Judge | — | general | 2026-05 |
| When Models Should Stay Silent | general | 2026-05 | |
| Benchmark-driven Time-Series-Augmented Generation | fintech | 2025-05 | |
| Tackling AI Hallucinations in LLM Apps | saas-b2b | 2025-02 | |
| Path to high-quality LLM-based Dasher support automation | food-delivery | 2024-09 | |
| A Hallucination Detector in RAG SystemsFR | FR | general | 2024-05 |
Improving the reliability of generative models: an approach to evaluating responses and data preparation![]() | ![]() | search-engine | 2023-10 |
| Siren Song in the Sea of AI: Hallucinations of Language Models | — | general | 2023-10 |
