mlsanityData to 14 Oct 2026

On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation

arXiv 2410.12222 ↗First posted 16 Oct 2024cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Hallucination has been a popular topic in natural language generation (NLG). In real-world applications, unfaithful content can result in poor data quality or loss of trust from end users. Thus, it is crucial to fact-check before adopting NLG for production usage, which can be expensive if done manually. In this paper, we investigate automated faithfulness evaluation in guided NLG. We developed a rubric template and used large language models (LLMs) to score the generation on quantifiable scales. We compared popular LLMs as well as widely adopted natural language inference (NLI) models in scoring quality and sensitivity. In addition, we developed methods for the generation of synthetic unfaithful data, as well as heuristics to quantify the percentage of hallucination. Our results on 4 travel-domain industry dataset show that GPT-4 can provide accurate judgement and explanation of whether a source and a generation are factually consistent. Furthermore, we found that tuning NLI models on synthetic data can improve performance. Lastly, we present insights on the latency and cost of deploying such a system.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 16 Oct 2024.

Builds on

20 of 39 references.

References · 20

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  8. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  9. 2024Qwen2 Technical Reportcited by 2,120
  10. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  11. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  12. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 445
8 more
  1. 2023Is ChatGPT a Good NLG Evaluator? A Preliminary Studycited by 422
  2. 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 407
  3. 2022On Decoding Strategies for Neural Text Generatorscited by 90
  4. 2023TrueTeacher: Learning Factual Consistency Evaluation with Large Language Modelscited by 83
  5. 2023Language models are not naysayers: An analysis of language models on negation benchmarkscited by 74
  6. 2022Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarizationcited by 34
  7. 2024Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negationcited by 15
  8. 2024Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topicscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Modelscited by 13
  2. 2025TravelBench : Exploring LLM Performance in Low-Resource Domainscited by 2
  3. 2026DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summariescited by 0
  4. 2026Not All That Is Fluent Is Factual: Investigating Hallucinations of Large Language Models in Academic Writingcited by 0