# Interpretable Unified Language Checking

arXiv: https://arxiv.org/abs/2304.03728 · HTML: https://mlsanity.com/paper/2304.03728/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 48 references that are in the map.
- First posted on arXiv 7 Apr 2023.

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://mlsanity.com/paper/2203.09509/) (2022)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [A Survey on Automated Fact-Checking](https://mlsanity.com/paper/2108.11896/) (2021)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [NewsQA: A Machine Comprehension Dataset](https://mlsanity.com/paper/1611.09830/) (2016)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Explainable Automated Fact-Checking for Public Health Claims](https://mlsanity.com/paper/2010.09926/) (2020)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information](https://mlsanity.com/paper/2106.05707/) (2021)
- [Faithful Reasoning Using Large Language Models](https://mlsanity.com/paper/2208.14271/) (2022)
- [Stance Detection with Bidirectional Conditional Encoding](https://mlsanity.com/paper/1606.05464/) (2016)

## Built on by (most cited first, 26 of 26)

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity](https://mlsanity.com/paper/2310.07521/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Searching for Best Practices in Retrieval-Augmented Generation](https://mlsanity.com/paper/2407.01219/) (2024)
- [Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting](https://mlsanity.com/paper/2407.08223/) (2024)
- [SAIL: Search-Augmented Instruction Learning](https://mlsanity.com/paper/2305.15225/) (2023)
- [How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances](https://mlsanity.com/paper/2310.07343/) (2023)
- [Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models](https://mlsanity.com/paper/2410.01782/) (2024)
- [RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions](https://mlsanity.com/paper/2501.00353/) (2024)
- [DataTales: Investigating the use of Large Language Models for Authoring Data-Driven Articles](https://mlsanity.com/paper/2308.04076/) (2023)
- [Zero-Resource Hallucination Prevention for Large Language Models](https://mlsanity.com/paper/2309.02654/) (2023)
- [RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation](https://mlsanity.com/paper/2502.10996/) (2025)
- [OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs](https://mlsanity.com/paper/2409.05152/) (2024)
- [STAND-Guard: A Small Task-Adaptive Content Moderation Model](https://mlsanity.com/paper/2411.05214/) (2024)
- [AutoHall: Automated Factuality Hallucination Dataset Generation for Large Language Models](https://mlsanity.com/paper/2310.00259/) (2023)
- [Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization](https://mlsanity.com/paper/2504.01018/) (2025)
- [SUGAR: Leveraging Contextual Confidence for Smarter Retrieval](https://mlsanity.com/paper/2501.04899/) (2025)
- [LUNA: A Model-Based Universal Analysis Framework for Large Language Models](https://mlsanity.com/paper/2310.14211/) (2023)
- [Retrieval-Augmented Recommendation Explanation Generation with Hierarchical Aggregation](https://mlsanity.com/paper/2507.09188/) (2025)
- [Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE](https://mlsanity.com/paper/2310.18581/) (2023)
- [Towards Lighter and Robust Evaluation for Retrieval Augmented Generation](https://mlsanity.com/paper/2503.16161/) (2025)
- [A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content](https://mlsanity.com/paper/2504.16120/) (2025)
- [Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment](https://mlsanity.com/paper/2603.07023/) (2026)

## 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.