References

• ACL Anthology - Tutorial Proposal: Hallucination in Large Language Models
  • LREC-COLING 2024 - Website for Hallucination in Large Language Models
  • Tutorial Proposal: Hallucination in Large Language Models - Slides
  • Github - LREC Coling hallunication tutorial
• Arxiv - Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis
• Arxiv - Lee, Nayeon, et al. Factuality enhanced language models for open-ended text generation.
• ACLAnthology - Ladhak, Faisal, et al. When do pre-training biases propagate to downstream tasks? a case study in text summarization.
• The Troubling Emergence of Hallucination in Large Language Models - An Extensive Definition, Quantification, and Prescriptive Remediations.
  • In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2541–2573, Singapore. Association for Computational Linguistics.
• Github - HaluEval

Python modules

• Github - LettuceDetect
  • Key Features:
    • Token-level precision: detect exact hallucinated spans
    • Optimized for inference: smaller model size and faster inference
    • 4K context window via ModernBERT
    • MIT-licensed models & code
    • HF Integration: one-line model loading
    • Easy to use python API: can be downloaded from pip and few lines of code to integrate into your RAG system