# Modeling Semantic Plausibility by Injecting World Knowledge

arXiv: https://arxiv.org/abs/1804.00619 · HTML: https://mlsanity.com/paper/1804.00619/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2018.

## Built on by (most cited first, 24 of 24)

- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge](https://mlsanity.com/paper/2109.01653/) (2021)
- [Event knowledge in large language models: the gap between the impossible and the unlikely](https://mlsanity.com/paper/2212.01488/) (2022)
- [Benchmarks for Automated Commonsense Reasoning: A Survey](https://mlsanity.com/paper/2302.04752/) (2023)
- [A Survey of Useful LLM Evaluation](https://mlsanity.com/paper/2406.00936/) (2024)
- [Editing Common Sense in Transformers](https://mlsanity.com/paper/2305.14956/) (2023)
- [Modeling Event Plausibility with Consistent Conceptual Abstraction](https://mlsanity.com/paper/2104.10247/) (2021)
- [Quantifying the Capabilities of LLMs across Scale and Precision](https://mlsanity.com/paper/2405.03146/) (2024)
- [Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge](https://mlsanity.com/paper/2107.10922/) (2021)
- [A Dataset for Physical and Abstract Plausibility and Sources of Human Disagreement](https://mlsanity.com/paper/2404.04035/) (2024)
- [How Inclusively do LMs Perceive Social and Moral Norms?](https://mlsanity.com/paper/2502.02696/) (2025)
- [Autoencoding Language Model Based Ensemble Learning for Commonsense Validation and Explanation](https://mlsanity.com/paper/2204.03324/) (2022)
- [Made of Steel? Learning Plausible Materials for Components in the Vehicle Repair Domain](https://mlsanity.com/paper/2304.14745/) (2023)
- [Shades of Zero: Distinguishing Impossibility from Inconceivability](https://mlsanity.com/paper/2502.20469/) (2025)
- [Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility](https://mlsanity.com/paper/2510.08091/) (2025)
- [Investigating the Nature of Disagreements on Mid-Scale Ratings: A Case Study on the Abstractness-Concreteness Continuum](https://mlsanity.com/paper/2311.04563/) (2023)
- [From Correlation to Causation: Understanding Climate Change through Causal Analysis and LLM Interpretations](https://mlsanity.com/paper/2412.16691/) (2024)
- [Semantic Novelty Detection and Characterization in Factual Text Involving Named Entities](https://mlsanity.com/paper/2210.17440/) (2022)
- [Plausible-Parrots @ MSP2023: Enhancing Semantic Plausibility Modeling using Entity and Event Knowledge](https://mlsanity.com/paper/2408.16937/) (2024)
- [Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility](https://mlsanity.com/paper/2503.12667/) (2025)
- [Modelling Adjectival Modification Effects on Semantic Plausibility](https://mlsanity.com/paper/2507.21828/) (2025)
- [Contextualising (Im)plausible Events Triggers Figurative Language](https://mlsanity.com/paper/2604.07885/) (2026)
- [Entity tracking emerges in sub-billion parameter language models and exceeds human performance in naturalistic narratives](https://mlsanity.com/paper/2608.18083/) (2026)

## Abstract (arXiv)

Distributional data tells us that a man can swallow candy, but not that a man can swallow a paintball, since this is never attested. However both are physically plausible events. This paper introduces the task of semantic plausibility: recognizing plausible but possibly novel events. We present a new crowdsourced dataset of semantic plausibility judgments of single events such as "man swallow paintball". Simple models based on distributional representations perform poorly on this task, despite doing well on selection preference, but injecting manually elicited knowledge about entity properties provides a substantial performance boost. Our error analysis shows that our new dataset is a great testbed for semantic plausibility models: more sophisticated knowledge representation and propagation could address many of the remaining errors.