# Entailment Semantics Can Be Extracted from an Ideal Language Model

arXiv: https://arxiv.org/abs/2209.12407 · HTML: https://mlsanity.com/paper/2209.12407/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?](https://mlsanity.com/paper/2104.10809/) (2021)

## Built on by (most cited first, 10 of 10)

- [A Latent Space Theory for Emergent Abilities in Large Language Models](https://mlsanity.com/paper/2304.09960/) (2023)
- [DALL-E 2 Fails to Reliably Capture Common Syntactic Processes](https://mlsanity.com/paper/2210.12889/) (2022)
- [Dissociating language and thought in large language models](https://mlsanity.com/paper/2301.06627/) (2023)
- [Do Language Models' Words Refer?](https://mlsanity.com/paper/2308.05576/) (2023)
- [Are Language Models Worse than Humans at Following Prompts? It's Complicated](https://mlsanity.com/paper/2301.07085/) (2023)
- [Can You Learn Semantics Through Next-Word Prediction? The Case of Entailment](https://mlsanity.com/paper/2402.13956/) (2024)
- [A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus](https://mlsanity.com/paper/2405.11877/) (2024)
- [Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds](https://mlsanity.com/paper/2305.14785/) (2023)
- [Strong hallucinations from negation and how to fix them](https://mlsanity.com/paper/2402.10543/) (2024)
- [For Generated Text, Is NLI-Neutral Text the Best Text?](https://mlsanity.com/paper/2302.08577/) (2023)

## Abstract (arXiv)

Language models are often trained on text alone, without additional grounding. There is debate as to how much of natural language semantics can be inferred from such a procedure. We prove that entailment judgments between sentences can be extracted from an ideal language model that has perfectly learned its target distribution, assuming the training sentences are generated by Gricean agents, i.e., agents who follow fundamental principles of communication from the linguistic theory of pragmatics. We also show entailment judgments can be decoded from the predictions of a language model trained on such Gricean data. Our results reveal a pathway for understanding the semantic information encoded in unlabeled linguistic data and a potential framework for extracting semantics from language models.