# Measure More, Question More: Experimental Studies on Transformer-based Language Models and Complement Coercion

arXiv: https://arxiv.org/abs/2212.10536 · HTML: https://mlsanity.com/paper/2212.10536/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 57 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 16 of 16)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains](https://mlsanity.com/paper/2102.12206/) (2021)
- [Word Acquisition in Neural Language Models](https://mlsanity.com/paper/2110.02406/) (2021)
- [Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses](https://mlsanity.com/paper/2104.14694/) (2021)
- [It's not Rocket Science : Interpreting Figurative Language in Narratives](https://mlsanity.com/paper/2109.00087/) (2021)
- [He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics](https://mlsanity.com/paper/2107.00807/) (2021)
- [Text-based NP Enrichment](https://mlsanity.com/paper/2109.12085/) (2021)
- [The Extraordinary Failure of Complement Coercion Crowdsourcing](https://mlsanity.com/paper/2010.05971/) (2020)

## Abstract (arXiv)

Transformer-based language models have shown strong performance on an array of natural language understanding tasks. However, the question of how these models react to implicit meaning has been largely unexplored. We investigate this using the complement coercion phenomenon, which involves sentences like "The student finished the book about sailing" where the action "reading" is implicit. We compare LMs' surprisal estimates at various critical sentence regions in sentences with and without implicit meaning. Effects associated with recovering implicit meaning were found at a critical region other than where sentences minimally differ. We then use follow-up experiments to factor out potential confounds, revealing different perspectives that offer a richer and more accurate picture.