mlsanityData to 14 Oct 2026

SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection

arXiv 2408.12748 ↗First posted 22 Aug 2024cs.CL cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are highly capable but face latency challenges in real-time applications, such as conducting online hallucination detection. To overcome this issue, we propose a novel framework that leverages a small language model (SLM) classifier for initial detection, followed by a LLM as constrained reasoner to generate detailed explanations for detected hallucinated content. This study optimizes the real-time interpretable hallucination detection by introducing effective prompting techniques that align LLM-generated explanations with SLM decisions. Empirical experiment results demonstrate its effectiveness, thereby enhancing the overall user experience.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 37 references that are in the map. First posted on arXiv 22 Aug 2024.

Builds on

29 of 37 references.

References · 29

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  3. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  4. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  5. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  6. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  7. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  8. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 367
  9. 2022News Summarization and Evaluation in the Era of GPT-3cited by 327
  10. 2023AlignScore: Evaluating Factual Consistency with a Unified Alignment Functioncited by 288
  11. 2021Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metricscited by 287
  12. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
17 more
  1. 2023Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solvecited by 178
  2. 2022The Unreliability of Explanations in Few-shot Prompting for Textual Reasoningcited by 169
  3. 2021Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarizationcited by 129
  4. 2021Reframing Human-AI Collaboration for Generating Free-Text Explanationscited by 125
  5. 2021Entity-level Factual Consistency of Abstractive Text Summarizationcited by 118
  6. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 108
  7. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  8. 2021Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Featurescited by 74
  9. 2020Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraintscited by 48
  10. 2020Generating Representative Headlines for News Storiescited by 39
  11. 2023Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinationscited by 35
  12. 2024Properties and Challenges of LLM-Generated Explanationscited by 24
  13. 2021Sketch and Refine: Towards Faithful and Informative Table-to-Text Generationcited by 21
  14. 2024Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detectorcited by 20
  15. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  16. 2023"Why is this misleading?": Detecting News Headline Hallucinations with Explanationscited by 17
  17. 2024LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoningcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 49
  2. 2025Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Modelscited by 7
  3. 2024Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learningcited by 2
  4. 2026Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibrationcited by 0