# Natural Language Decompositions of Implicit Content Enable Better Text Representations

arXiv: https://arxiv.org/abs/2305.14583 · HTML: https://mlsanity.com/paper/2305.14583/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 82 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 26 of 26)

- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings](https://mlsanity.com/paper/1904.01596/) (2019)
- [Generating Literal and Implied Subquestions to Fact-check Complex Claims](https://mlsanity.com/paper/2205.06938/) (2022)
- [Classification and Clustering of Arguments with Contextualized Word Embeddings](https://mlsanity.com/paper/1906.09821/) (2019)
- [SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features](https://mlsanity.com/paper/2206.07023/) (2022)
- [Misinfo Reaction Frames: Reasoning about Readers' Reactions to News Headlines](https://mlsanity.com/paper/2104.08790/) (2021)
- [Measuring the Similarity of Sentential Arguments in Dialog](https://mlsanity.com/paper/1709.01887/) (2017)
- [Text-Based Ideal Points](https://mlsanity.com/paper/2005.04232/) (2020)
- [What do Large Language Models Learn about Scripts?](https://mlsanity.com/paper/2112.13834/) (2021)
- [Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections](https://mlsanity.com/paper/2305.05094/) (2023)
- [The Universal Decompositional Semantics Dataset and Decomp Toolkit](https://mlsanity.com/paper/1909.13851/) (2019)

## Built on by (most cited first, 19 of 19)

- [Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?](https://mlsanity.com/paper/2402.12483/) (2024)
- [AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora](https://mlsanity.com/paper/2505.23628/) (2025)
- [Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas](https://mlsanity.com/paper/2501.11549/) (2025)
- [Accurate and Nuanced Open-QA Evaluation Through Textual Entailment](https://mlsanity.com/paper/2405.16702/) (2024)
- [Interpretable Text Embeddings and Text Similarity Explanation: A Survey](https://mlsanity.com/paper/2502.14862/) (2025)
- [Conversational User-AI Intervention: A Study on Prompt Rewriting for Improved LLM Response Generation](https://mlsanity.com/paper/2503.16789/) (2025)
- [Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning](https://mlsanity.com/paper/2506.08354/) (2025)
- [BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle](https://mlsanity.com/paper/2502.18331/) (2025)
- ["We Demand Justice!": Towards Social Context Grounding of Political Texts](https://mlsanity.com/paper/2311.09106/) (2023)
- [Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat Logs](https://mlsanity.com/paper/2503.12370/) (2025)
- [Talking Point based Ideological Discourse Analysis in News Events](https://mlsanity.com/paper/2504.07400/) (2025)
- [Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework](https://mlsanity.com/paper/2508.12257/) (2025)
- [TopicGPT: A Prompt-based Topic Modeling Framework](https://mlsanity.com/paper/2311.01449/) (2023)
- [Tell, Don't Show: Leveraging Language Models' Abstractive Retellings to Model Literary Themes](https://mlsanity.com/paper/2505.23166/) (2025)
- [ConceptCarve: Dynamic Realization of Evidence](https://mlsanity.com/paper/2504.07228/) (2025)
- [Learning to Diagnose and Correct Moral Errors: Beyond Shallow Heuristics in Moral Alignment](https://mlsanity.com/paper/2601.03079/) (2026)
- [Large Language Model and Formal Concept Analysis: a comparative study for Topic Modeling](https://mlsanity.com/paper/2602.01933/) (2026)
- [Scene Abstraction for Lexical Semantics: Structured Representations of Situated Meaning](https://mlsanity.com/paper/2605.22542/) (2026)
- [Inductive Claims Extraction at Scale](https://mlsanity.com/paper/2610.05275/) (2026)

## Abstract (arXiv)

When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been observed, then validate the plausibility of the generated content via human judgments. Incorporating these explicit representations of implicit content proves useful in multiple problem settings that involve the human interpretation of utterances: assessing the similarity of arguments, making sense of a body of opinion data, and modeling legislative behavior. Our results suggest that modeling the meanings behind observed language, rather than the literal text alone, is a valuable direction for NLP and particularly its applications to social science.