mlsanityData to 7 Oct 2026

Interpretable Unified Language Checking

arXiv 2304.03728 ↗First posted 7 Apr 2023cs.CLcited by 26

Not on the map. Why?

Abstract (arXiv)

Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations of natural and social knowledge. We present an interpretable, unified, language checking (UniLC) method for both human and machine-generated language that aims to check if language input is factual and fair. While fairness and fact-checking tasks have been handled separately with dedicated models, we find that LLMs can achieve high performance on a combination of fact-checking, stereotype detection, and hate speech detection tasks with a simple, few-shot, unified set of prompts. With the ``1/2-shot'' multi-task language checking method proposed in this work, the GPT3.5-turbo model outperforms fully supervised baselines on several language tasks. The simple approach and results suggest that based on strong latent knowledge representations, an LLM can be an adaptive and explainable tool for detecting misinformation, stereotypes, and hate speech.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 7 Apr 2023.

Builds on

37 of 48 references.

References · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  8. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  9. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  10. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  11. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  12. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
25 more
  1. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  3. 2019Defending Against Neural Fake Newscited by 553
  4. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  5. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  6. 2021A Survey on Automated Fact-Checkingcited by 376
  7. 2017"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detectioncited by 361
  8. 2016NewsQA: A Machine Comprehension Datasetcited by 330
  9. 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 222
  10. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 215
  11. 2018Gender Bias in Neural Natural Language Processingcited by 210
  12. 2020Explainable Automated Fact-Checking for Public Health Claimscited by 209
  13. 2022Predictability and Surprise in Large Generative Modelscited by 209
  14. 2018Hate Speech Dataset from a White Supremacy Forumcited by 196
  15. 2020CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claimscited by 195
  16. 2021FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured informationcited by 166
  17. 2022Faithful Reasoning Using Large Language Modelscited by 130
  18. 2016Stance Detection with Bidirectional Conditional Encodingcited by 93
  19. 2021Towards generalisable hate speech detection: a review on obstacles and solutionscited by 66
  20. 2019The Limitations of Stylometry for Detecting Machine-Generated Fake Newscited by 63
  21. 2021Detecting Hate Speech with GPT-3cited by 55
  22. 2019#MeTooMA: Multi-Aspect Annotations of Tweets Related to the MeToo Movementcited by 15
  23. 2019FAKTA: An Automatic End-to-End Fact Checking Systemcited by 13
  24. 2023Logic Against Bias: Textual Entailment Mitigates Stereotypical Sentence Reasoningcited by 7
  25. 2021Creation and Evaluation of a Pre-tertiary Artificial Intelligence (AI) Curriculumcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 6; 2025: 6; 2026: 1.

26 papers.

Sort:

By area:

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  2. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  3. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  4. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 204
  5. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 202
  6. 2023Can LLM-Generated Misinformation Be Detected?cited by 173
  7. 2024Searching for Best Practices in Retrieval-Augmented Generationcited by 83
  8. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 76
  9. 2023SAIL: Search-Augmented Instruction Learningcited by 33
  10. 2023How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advancescited by 33
  11. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25
  12. 2024RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructionscited by 25
14 more
  1. 2023DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articlescited by 24
  2. 2023Zero-Resource Hallucination Prevention for Large Language Modelscited by 19
  3. 2025RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generationcited by 16
  4. 2024OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMscited by 14
  5. 2024STAND-Guard: A Small Task-Adaptive Content Moderation Modelcited by 11
  6. 2023AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Modelscited by 10
  7. 2025Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalizationcited by 9
  8. 2025SUGAR: Leveraging Contextual Confidence for Smarter Retrievalcited by 6
  9. 2023LUNA: A Model-Based Universal Analysis Framework for Large Language Modelscited by 4
  10. 2025Retrieval-Augmented Recommendation Explanation Generation with Hierarchical Aggregationcited by 2
  11. 2023Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITEcited by 1
  12. 2025Towards Lighter and Robust Evaluation for Retrieval Augmented Generationcited by 0
  13. 2025A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Contentcited by 0
  14. 2026Hit-RAG: Learning to Reason with Long Contexts via Preference Alignmentcited by 0