mlsanityData to 14 Oct 2026

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis

arXiv 2312.16374 ↗First posted 27 Dec 2023cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have revolutionized various domains with extensive knowledge and creative capabilities. However, a critical issue with LLMs is their tendency to produce outputs that diverge from factual reality. This phenomenon is particularly concerning in sensitive applications such as medical consultation and legal advice, where accuracy is paramount. In this paper, we introduce the LLM factoscope, a novel Siamese network-based model that leverages the inner states of LLMs for factual detection. Our investigation reveals distinguishable patterns in LLMs' inner states when generating factual versus non-factual content. We demonstrate the LLM factoscope's effectiveness across various architectures, achieving over 96% accuracy in factual detection. Our work opens a new avenue for utilizing LLMs' inner states for factual detection and encourages further exploration into LLMs' inner workings for enhanced reliability and transparency.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 27 Dec 2023.

Builds on

25 of 49 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  7. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  8. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  9. 2022Mass-Editing Memory in a Transformercited by 1,001
  10. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 812
  11. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 810
  12. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
13 more
  1. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 767
  2. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  3. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 712
  4. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  5. 2023The Internal State of an LLM Knows When It's Lyingcited by 659
  6. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 532
  7. 2023Augmented Language Models: a Surveycited by 403
  8. 2023HuatuoGPT, towards Taming Language Model to Be a Doctorcited by 214
  9. 2023The Hydra Effect: Emergent Self-repair in Language Model Computationscited by 156
  10. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  11. 2017Natural Language Processing: State of The Art, Current Trends and Challengescited by 114
  12. 2023Overthinking the Truth: Understanding how Language Models Process False Demonstrationscited by 81
  13. 2023Good-looking but Lacking Faithfulness: Understanding Local Explanation Methods through Trend-based Testingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 4.

7 papers.

  1. 2024Interpreting and Editing Vision-Language Representations to Mitigate Hallucinationscited by 104
  2. 2025Lightweight Latent Verifiers for Efficient Meta-Generation Strategiescited by 3
  3. 2025Exploring How LLMs Capture and Represent Domain-Specific Knowledgecited by 3
  4. 2026The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Modelscited by 2
  5. 2026Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clusteringcited by 1
  6. 2026From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMscited by 0
  7. 2026CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Modelscited by 0